AI Security

Vulnerabilities, red teaming, safety, alignment, defenses

678 articles across 186 editions

Articles

  1. [Editorial] -- 2026-02-24
  2. [Editorial] -- 2026-02-24
  3. In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach -- 2026-02-24
  4. [Editorial] -- 2026-02-24
  5. [Editorial] -- 2026-02-24
  6. [Editorial] -- 2026-02-24
  7. [Editorial] -- 2026-02-24
  8. [Editorial] -- 2026-02-24
  9. BakeLens/crust -- 2026-02-24
  10. hazcod/claudleak -- 2026-02-24
  11. [Editorial] Bugcrowd Guide to Prompt Injection -- 2026-02-23
  12. [Editorial] arXiv Research -- 2026-02-23
  13. [Editorial] Exploitation Validator -- 2026-02-23
  14. What Breaks Embodied AI Security: LLM Vulnerabilities, CPS Flaws, or Something Else? -- 2026-02-23
  15. Zero-day CSS: CVE-2026-2441 exists in the wild -- 2026-02-21
  16. Microsoft says bug causes Copilot to summarize confidential emails -- 2026-02-21
  17. [Editorial] WebMCP — MCP for the Web -- 2026-02-21
  18. [Editorial] Anthropic: Claude Code Security -- 2026-02-21
  19. [Editorial] Video: AI Technology Deep Dive -- 2026-02-21
  20. [Editorial] Lonkero — Open Source AI Tool -- 2026-02-21
  21. [Editorial] RSAC Security Conference Insights -- 2026-02-21
  22. [Editorial] CSA Policy on Personal AI Desktop Agents -- 2026-02-21
  23. Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge -- 2026-02-21
  24. [Editorial] RTI Genesis — Real-Time Infrastructure -- 2026-02-21
  25. [Editorial] RuVector & RVF Vector Database -- 2026-02-21
  26. [Editorial] RVDNA — Does It Work? -- 2026-02-21
  27. AI45Lab/TrinityGuard: A Unified Framework for Safeguarding Multi-Agent System Safety -- 2026-02-20
  28. HackMyClaw — Adversarial Security Challenge for AI Agents -- 2026-02-20
  29. [Editorial] Video Feature -- 2026-02-20
  30. [Editorial] LinkedIn Identity Verification Privacy Concerns -- 2026-02-20
  31. WARNING: Your "Deleted" Grok data might still be publicly accessible -- 2026-02-20
  32. Is Google running a secret RAG layer? Gemini's 'impossible' cross-session memory -- 2026-02-20
  33. [Editorial] AI Security, Governance, and Cybersecurity -- 2026-02-19
  34. AI-generated password isn't random, it just looks that way -- 2026-02-19
  35. [Editorial] Ghostcss -- 2026-02-18
  36. [Editorial] Cybersecurity AI Vulnerability -- 2026-02-18
  37. [Editorial] ProjectMemory -- 2026-02-18
  38. [Editorial] Cybersecurity MCP AI Agents -- 2026-02-18
  39. [Editorial] Shannon by Keygraph -- 2026-02-18
  40. [Editorial] AI Community Discussion -- 2026-02-18
  41. HackingDave/btrpa-scan — BLE Scanner with RPA Resolution -- 2026-02-18
  42. I built a local AI coding agent with an 8-layer security sandbox — then had ChatGPT try to break it for 240+ rounds -- 2026-02-18
  43. [Editorial] How to Sandbox Claude Code with Nono -- 2026-02-18
  44. tomascupr/sandstorm — One API call. Full Claude agent. Completely sandboxed. -- 2026-02-18
  45. [Editorial] AI Agent Security Strategy -- 2026-02-18
  46. [Editorial] Agenda for the UnPrompted AI Security Conference is out now -- 2026-02-17
  47. How cyborg propaganda reshapes collective action -- 2026-02-17
  48. [Editorial] ICML Conference Organizers Insert Instructions for AI Reviewers -- 2026-02-17
  49. [Editorial] Neural Network Training on New Tasks -- 2026-02-17
  50. Hamming Distance for Hybrid Search in SQLite -- 2026-02-17
  51. [Editorial] Saturday AI Musings — 1979 Film -- 2026-02-17
  52. [Editorial] Context Drift: How I Talked AI Agents Into Giving Up Their Secrets -- 2026-02-16
  53. [Editorial] PromptArmor — AI Security Defense -- 2026-02-16
  54. [Editorial] The Agentic AI Future of Threat Intelligence -- 2026-02-16
  55. [Editorial] ClawdInt — Agentic AI Threat Intelligence -- 2026-02-16
  56. [Editorial] Discovering Negative-Day Vulnerabilities in LLM Workflows -- 2026-02-16
  57. [Editorial] Wiz AI Cyber Model Arena: Real-World Benchmark for AI Agents in Cybersecurity -- 2026-02-16
  58. [Editorial] Video Content -- 2026-02-16
  59. [Editorial] Expanding UnicornScan — Security Scanning with AI -- 2026-02-16
  60. unicornscan.org -- 2026-02-16
  61. [Editorial] https://arxiv.org/abs/2602.10117 -- 2026-02-13
  62. [Editorial] https://arxiv.org/abs/2602.09433 -- 2026-02-13
  63. [Editorial] https://www.linkedin.com/posts/hermanerrico_i-put-out-a-site-and-paper-defining-a-new-activity-7427822997593387008-zzYm -- 2026-02-13
  64. [Editorial] https://www.linkedin.com/pulse/ive-spent-three-decades-cybersecurity-ai-biggest-trust-brett-kelsey-v7r3c -- 2026-02-13
  65. [Editorial] https://www.linkedin.com/pulse/ai-red-teamers-advice-orgs-deploying-brian-chamberlain-utkse -- 2026-02-13
  66. [Editorial] https://www.linkedin.com/posts/cole-medin-727752184_vibe-coding-has-a-30-50-security-vulnerability-activity-7420461997537959938-y5uG -- 2026-02-13
  67. [Editorial] https://zeltser.com/ai-malware-analysis-remnux -- 2026-02-13
  68. [Editorial] https://www.authsignal.com/blog/articles/account-recovery-is-the-identity-industrys-most-overlooked-challenge -- 2026-02-13
  69. [Editorial] https://raffy.ch/blog/2026/02/03/the-gaps-that-created-the-new-wave-of-siem-and-ai-soc-vendors -- 2026-02-13
  70. [Editorial] https://m.youtube.com/watch?v=w8p-yFqF13o -- 2026-02-13
  71. [Editorial] https://www.microsoft.com/en-us/security/blog/2026/02/10/ai-recommendation-poisoning -- 2026-02-12
  72. ICE knocks on ad tech's data door to see what it knows about you -- 2026-02-12
  73. [Editorial] https://www.linkedin.com/posts/caleb-gross_agentic-llms-can-automate-vuln-detection-ugcPost-7427011167098777601-Xu0o -- 2026-02-11
  74. [Editorial] https://www.linkedin.com/posts/resilientcyber_probabilistic-tcb-activity-7427078167754113024-4XQN -- 2026-02-11
  75. [Editorial] https://www.linkedin.com/posts/yass-99637a105_this-last-month-ive-been-working-on-creating-activity-7427059163681325056-9q55 -- 2026-02-11
  76. [Editorial] https://arxiv.org/abs/2507.02735 -- 2026-02-11
  77. [Editorial] https://youtu.be/tW6OWmYEX44 -- 2026-02-10
  78. [Editorial] https://www.microsoft.com/en-us/security/blog/2026/02/09/prompt-attack-breaks-llm-safety -- 2026-02-10
  79. [Editorial] https://goteleport.com/platform/ai-infrastructure -- 2026-02-10
  80. ChatGPT repeated back our internal API documentation almost word for word -- 2026-02-10
  81. [Editorial] https://www.linkedin.com/posts/ownyourai_i-just-open-sourced-my-security-auditor-for-activity-7426565421375541248-rqGu -- 2026-02-09
  82. [Editorial] https://www.linkedin.com/posts/activity-7426382890004971520-VBdy -- 2026-02-09
  83. [Editorial] https://www.linkedin.com/posts/samuele-giampieri-b1b67597_redamon-airedteam-penetrationtesting-activity-7426292400534437889--0Ny -- 2026-02-09
  84. [Editorial] https://hackernoon.com/everyone-says-ai-is-insecure-so-i-measured-it -- 2026-02-09
  85. [Editorial] https://x.com/fr0gger_/status/2020025525784514671?ct=rw-li -- 2026-02-09
  86. Agent deleted production data because no policy layer said 'no' - what's your governance strategy? -- 2026-02-09
  87. [Editorial] https://red.anthropic.com/2026/zero-days -- 2026-02-06
  88. 1-Click RCE to steal your Moltbot data and keys -- 2026-02-06
  89. Hacking Moltbook -- 2026-02-06
  90. Built an open-source chat UI with message editing, branching, and E2E encrypted phone sync - works with any model via OpenClaw -- 2026-02-06
  91. OpenClaw Assistant - Privacy-first Android voice assistant with OpenAI-compatible API support -- 2026-02-06
  92. [Editorial] https://github.com/usestrix/strix -- 2026-02-06
  93. [Editorial] https://github.com/GH05TCREW/pentestagent -- 2026-02-06
  94. [Editorial] https://www.edloveless.com/the-call-is-coming-from-inside-the-house-and-its-watching-netflix -- 2026-02-06
  95. eScan Antivirus Delivers Malware in Supply Chain Attack -- 2026-02-06
  96. [Editorial] https://www.linkedin.com/posts/rssk_detecting-backdoored-language-models-activity-7424871629530284034-tYq6 -- 2026-02-05
  97. [Editorial] https://www.linkedin.com/posts/hermanerrico_aisecurity-agenticai-cybersecurity-activity-7424484799123247104-40_F -- 2026-02-04
  98. m4xxxxx/AIxVuln -- 2026-02-04
  99. safedep/gryph -- 2026-02-03
  100. Prek: A better, faster, drop-in pre-commit replacement, engineered in Rust -- 2026-02-03
  101. [Editorial] https://zeroleaks.ai/reports/openclaw-analysis.pdf -- 2026-02-02
  102. [Editorial] https://www.linkedin.com/posts/alex-polyakov-cyber_owasp-cascading-failures-in-agentic-ai-101-activity-7422268062101356546-VMFq -- 2026-02-02
  103. [Editorial] https://blogs.cisco.com/ai/personal-ai-agents-like-openclaw-are-a-security-nightmare -- 2026-02-02
  104. i just saw this ClawdBot RCE demo on X… are we cooked? -- 2026-02-02
  105. County pays $600k to pentesters it arrested for assessing courthouse security -- 2026-01-30
  106. The Hallucination Defense -- 2026-01-30
  107. [Editorial] https://github.com/FuzzingLabs/mcp-security-hub -- 2026-01-29
  108. [Editorial] https://www.runtime.news/ai-slop-is-overwhelming-open-source -- 2026-01-29
  109. [Editorial] https://blogs.cisco.com/ai/personal-ai-agents-like-moltbot-are-a-security-nightmare -- 2026-01-29
  110. Running local AI agents scared me into building security practices -- 2026-01-29
  111. Six JavaScript zero-day bugs lead to fears of supply chain attack -- 2026-01-29
  112. Europe wants to end its dangerous reliance on US internet technology -- 2026-01-27
  113. Can Skynet Be a Statesman? -- 2026-01-27
  114. [Editorial] https://grahamhelton.com/blog/nodes-proxy-rce -- 2026-01-26
  115. Route leak incident on January 22, 2026 -- 2026-01-26
  116. [Editorial] https://www.linkedin.com/posts/owais-drera-590750378_github-owaisdreraagent-slayer-activity-7419782518985486336-7WE3 -- 2026-01-23
  117. [Editorial] https://www.linkedin.com/posts/resilientcyber_prompt-injection-activity-7420165497230454784-NOHa -- 2026-01-23
  118. [Editorial] https://www.linkedin.com/posts/anshumanbhartiya_lets-talk-about-threat-modeling-and-skills-activity-7418130148312674305-arTh -- 2026-01-23
  119. [Editorial] https://www.linkedin.com/posts/reuvencohen_introducing-prime-radiant-a-real-time-activity-7420466084006223873-hOct -- 2026-01-23
  120. [Editorial] https://www.wiz.io/blog/wiz-research-codebreach-vulnerability-aws-codebuild -- 2026-01-23
  121. There's a hidden Android setting that spots fake cell towers -- 2026-01-23
  122. TerabyteDeals – Compare storage prices by $/TB -- 2026-01-23
  123. [Editorial] https://www.linkedin.com/posts/activity-7419736138325696512-R0qY -- 2026-01-22
  124. [Editorial] https://www.linkedin.com/posts/robvanderveer_ai-aisecurity-activity-7419684559086161920-XYNF -- 2026-01-22
  125. [Editorial] https://blog.securitybreak.io/coding-agents-the-insider-threat-you-installed-yourself-35644a1d5409 -- 2026-01-22
  126. I scanned 2,500 Hugging Face models for malware/issues. Here is the data -- 2026-01-22
  127. Provably unmasking malicious behavior through execution traces -- 2026-01-22
  128. [Resource] AI Guardrails: Open-source middleware to add PII Redaction & Injection Defense to local LLMs -- 2026-01-21
  129. Jailbreak Challenge: Can You Break My Agent??? -- 2026-01-21
  130. Do AI agents need TLS-style identities and ‘certificates’? -- 2026-01-21
  131. Drone Hacking Part 1: Dumping Firmware and Bruteforcing ECC -- 2026-01-21
  132. Looking at a Real Fake Raspberry Pi RP2040 Board -- 2026-01-21
  133. What I learned after almost losing important files to Cowork (and how I set it up safely now) -- 2026-01-20
  134. Project Fail: Cracking a Laptop BIOS Password Using AI -- 2026-01-20
  135. [Editorial] https://sean.heelan.io/2026/01/18/on-the-coming-industrialisation-of-exploit-generation-with-llms -- 2026-01-19
  136. [Editorial] https://red.anthropic.com/2026/cyber-toolkits-update -- 2026-01-19
  137. [Editorial] https://github.com/trailofbits/skills -- 2026-01-19
  138. [Editorial] https://engineering.block.xyz/blog/how-we-red-teamed-our-own-ai-agent- -- 2026-01-16
  139. [Editorial] https://arxiv.org/html/2601.09625v1 -- 2026-01-16
  140. [Editorial] https://appomni.com/ao-labs/bodysnatcher-agentic-ai-security-vulnerability-in-servicenow -- 2026-01-16
  141. [Editorial] https://arxiv.org/abs/2601.09625 -- 2026-01-16
  142. ssmvl2/Nextjs-RCE-Exploit -- 2026-01-16
  143. [Editorial] https://www.usenix.org/system/files/usenixsecurity25-zhang-xiang.pdf -- 2026-01-16
  144. [Editorial] https://state-of-iranblackout.whisper.security/ -- 2026-01-16
  145. [Editorial] https://equixly.com/blog/2026/01/14/can-ai-identify-0days -- 2026-01-16
  146. [Editorial] https://www.linkedin.com/pulse/ai-race-moving-faster-than-our-security-standards-can-david-abutbul-zmvtf -- 2026-01-15
  147. [Editorial] https://www.linkedin.com/posts/josh-orenstein_iran-just-did-something-no-government-has-activity-7417294442811895811-oOTR -- 2026-01-15
  148. [Editorial] https://sanderschulhoff.substack.com/p/the-ai-security-industry-is-bullshit -- 2026-01-15
  149. [Editorial] https://hackthemodel.com/ai-security-isnt-bullshit-but-we-re-securing-the-wrong-thing-b925d04b517a -- 2026-01-15
  150. [Editorial] https://www.linkedin.com/posts/reuvencohen_qudag-bitchat-is-a-secure-peer-to-peer-messaging-activity-7417222548897329152-153E -- 2026-01-15
  151. Confer – End to end encrypted AI chat -- 2026-01-15
  152. [Editorial] https://www.darkreading.com/remote-workforce/ai-vulnerability-servicenow -- 2026-01-14
  153. [Editorial] https://www.rockcybermusings.com/p/ai-attacker-advantage-is-a-myth -- 2026-01-14
  154. [Editorial] https://www.phoronix.com/news/First-Linux-Rust-CVE -- 2026-01-14
  155. [Editorial] https://techcommunity.microsoft.com/blog/educatordeveloperblog/zero-trust-agent-architecture-how-to-actually-secure-your-agents/4473995 -- 2026-01-14
  156. The Concerning Amount of Malware on the VS Code Marketplace -- 2026-01-13
  157. Data Exfiltration via DNS Resolution -- 2026-01-13
  158. The No Fakes Act has a “fingerprinting” trap that kills open source? -- 2026-01-13
  159. sardanioss/httpcloak -- 2026-01-13
  160. Making a CRT Spin Right Round, Round, Round -- 2026-01-13
  161. [Editorial] https://blog.openthreatresearch.com/evolving-the-threat-hunter-playbook-planning-hunts-with-agent-skills -- 2026-01-12
  162. [Editorial] https://maggiegray.us/p/the-age-of-ai-for-offensive-cyber -- 2026-01-12
  163. [Editorial] https://www.linkedin.com/posts/resilientcyber_llm-fingerprinting-activity-7415849264452739072-H9fw -- 2026-01-12
  164. [Editorial] https://www.linkedin.com/posts/johnbruggeman_kimwolf-tldr-whattodo-activity-7413983885392396289-xsd4 -- 2026-01-12
  165. [Editorial] https://www.linkedin.com/posts/clintgibler_cybersecurity-ai-activity-7407102282120462337-6URK -- 2026-01-12
  166. [Editorial] https://xoxruns.medium.com/feedback-driven-iteration-and-fully-local-webapp-pentesting-ai-agent-achieving-78-on-xbow-199ef719bf01 -- 2026-01-12
  167. [Editorial] https://www.linkedin.com/posts/yass-99637a105_i-spent-the-last-couple-of-months-building-activity-7415098924224499714-lCDV -- 2026-01-12
  168. [Editorial] https://www.linkedin.com/posts/rohankaushik1_when-opening-a-repository-is-enough-vs-code-activity-7414679374760882177-XaiC -- 2026-01-09
  169. AI45Lab/OpenRT -- 2026-01-09
  170. halilkirazkaya/arsenal-ng -- 2026-01-09
  171. [Editorial] https://www.linkedin.com/posts/daniel-cuthbert0x_last-year-i-spent-most-of-my-time-reviewing-activity-7414597548050665472-dYjg -- 2026-01-08
  172. Creating a bespoke data diode for air‑gapped networks -- 2026-01-08
  173. Don't Forget the WAL: How I Lost SQLite Data in Podman Containers -- 2026-01-08
  174. [Editorial] https://backalleycoder.com/posts/passseeds-an-experiment-in-hijacking-passkeys-to-unlock-cryptographic-use-cases -- 2026-01-07
  175. [Editorial] https://hackbot.dad/writing/intro-to-gpus -- 2026-01-07
  176. [Editorial] https://substack.com/inbox/post/183640704?triedRedirect=true -- 2026-01-06
  177. The Kimwolf Botnet Is Stalking Your Local Network -- 2026-01-06
  178. [Editorial] https://www.linkedin.com/feed/update/urn:li:ugcPost:7413902697625628675 -- 2026-01-05
  179. NYC Wegmans is storing biometric data on shoppers' eyes, voices and faces -- 2026-01-05
  180. [Release] Dingo v2.0 – Open-source AI data quality tool now supports SQL databases, RAG evaluation, and Agent-as-a-Judge hallucination detection! -- 2025-12-31
  181. Securing MCP in production -- 2025-12-31
  182. Binance's Trust Wallet extension hacked; users lose $7M -- 2025-12-30
  183. [Editorial] https://github.com/JohannesLks/CVE-2025-14558 -- 2025-12-29
  184. batterdaysahead/cipher0 -- 2025-12-29
  185. MongoBleed -- 2025-12-29
  186. [Editorial] https://www.linkedin.com/posts/cybersecurity-fredrikhansen_trained-a-24b-cybersecurity-llm-on-40k-security-ugcPost-7410736974162219008-Y28P -- 2025-12-29
  187. [Editorial] https://0din.ai/blog/sidekick -- 2025-12-29
  188. [Editorial] https://www.linkedin.com/posts/resilientcyber_proactive-defenses-against-llm-agents-ugcPost-7409283274495250432-hRCB -- 2025-12-29
  189. I built a benchmark to test which LLMs would kill you in the apocalypse. The answer: all of them, just in different ways. -- 2025-12-29
  190. [Editorial] https://www.linkedin.com/posts/harish-santhanalakshmi-ganesan-31ba96171_github-cisco-ai-defensemcp-scanner-scan-activity-7409036231025811456-y16c -- 2025-12-23
  191. [Editorial] PentestGPT -- 2025-12-23
  192. Untargeted Jailbreak Attack -- 2025-12-23
  193. AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems -- 2025-12-23
  194. [Editorial] https://bughunters.google.com/blog/4823857172971520/task-injection-exploiting-agency-of-autonomous-ai-agents -- 2025-12-22
  195. fatguru/CVE-2025-55182-scanner -- 2025-12-22
  196. omertheroot/flagrep -- 2025-12-22
  197. [Editorial] https://www.linkedin.com/posts/gadievron_announcing-unprompted-a-new-ai-security-activity-7407125529214005248-Pk6F -- 2025-12-18
  198. Browser 'privacy' extensions have eye on your AI, log all your chats -- 2025-12-18
  199. Most parked domains now serving malicious content -- 2025-12-18
  200. 8M users' AI conversations sold for profit by "privacy" extensions -- 2025-12-17
  201. [Editorial] https://github.com/schwartz1375/genai-security-training -- 2025-12-16
  202. Major Security Concern: Credits draining despite 2FA and deleted keys. Anyone else? -- 2025-12-16
  203. Opinion: US Authorities Have Far-Reaching Access to European Cloud Data -- 2025-12-16
  204. [Editorial] https://mindgard.ai/blog/google-antigravity-persistent-code-execution-vulnerability -- 2025-12-15
  205. [Editorial] https://www.linkedin.com/posts/jasonstanley2_trustworthyai-aisecurity-aisafety-activity-7405357983746109440-T6pE -- 2025-12-15
  206. It Only Takes a Handful of Samples To Poison Any Size LLM, Anthropic Finds -- 2025-12-15
  207. Price of a bot army revealed across online platforms -- 2025-12-15
  208. iOS 26.2 fixes 20 security vulnerabilities, 2 actively exploited -- 2025-12-15
  209. Litestream VFS -- 2025-12-15
  210. Portugal updates cybercrime law to exempt security researchers -- 2025-12-12
  211. hackersatyamrastogi/react2shell-ultimate -- 2025-12-12
  212. Xenov-X/csbot -- 2025-12-12
  213. This Week in Security: Hornet, Gogs, and Blinkenlights -- 2025-12-12
  214. SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security -- 2025-12-12
  215. Am I overthinking GDPR/Privacy by moving my AI workflow local? -- 2025-12-12
  216. Making Glasses That Detect Smartglasses -- 2025-12-11
  217. [Editorial] https://arxiv.org/abs/2511.20920 -- 2025-12-09
  218. The security risks of "Emoji Smuggling" and Hidden Prompts for Local Agents -- 2025-12-08
  219. deepseek-ai/DeepSeek-Math-V2 -- 2025-12-08
  220. Small numbers of Notepad++ users reporting security woes -- 2025-12-05
  221. 'Security Disaster'–500M Microsoft Users Say No to Windows 11 -- 2025-12-05
  222. Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications -- 2025-12-04
  223. [Editorial] https://www.linkedin.com/posts/ownyourai_nvidia-just-open-sourced-the-espresso-machine-activity-7401526786955812864-XUg2 -- 2025-12-02
  224. [Editorial] https://www.linkedin.com/posts/gadievron_introducing-raptor-an-autonomous-offensive-activity-7401533346238840832-6FxM -- 2025-12-02
  225. [Editorial] https://mavlevin.com/2025/11/30/cve-2022-35420-scada-lts-unauthenticated-account-takeover# -- 2025-12-02
  226. Belgian Police exposed using botnets to manipulate EU data law impact assessment -- 2025-12-01
  227. In Re: 23andMe, Inc. Customer Data Security Breach Litigation -- 2025-12-01
  228. Deep learning models are vulnerable, but adversarial examples are even more vulnerable -- 2025-12-01
  229. [Editorial] https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.700-2.pdf -- 2025-12-01
  230. [Editorial] https://github.com/aliasrobotics/cai -- 2025-12-01
  231. [Editorial] https://github.com/OWASP/www-project-ai-testing-guide/ -- 2025-12-01
  232. This Week in Security: Cloudflare Wasn’t DNS, BADAUDIO, and Not a Vuln -- 2025-11-28
  233. [Editorial] https://www.linkedin.com/posts/reuvencohen_the-hacker-news-discussion-around-agentic-share-7399084932138115073-gJAR -- 2025-11-25
  234. adrian13508/dockershield -- 2025-11-25
  235. k1lgor/container-diet -- 2025-11-25
  236. [Editorial] AI Worms -- 2025-11-24
  237. [Editorial] https://disesdi.substack.com/p/ai-red-teaming-has-a-subspace-problem -- 2025-11-24
  238. Anthropics Latest Research on Alignment Faking -- 2025-11-24
  239. Posthog NPM packages are compromised -- 2025-11-24
  240. [Editorial] Jailbreak -- 2025-11-21
  241. Anthropic - Disrupting the first reported AI-orchestrated cyber espionage campaign = "The threat actor—whom we assess with high confidence was a Chinese state-sponsored group" Link to report below -- 2025-11-21
  242. LuD1161/jsmon-go -- 2025-11-21
  243. Dissecting Flock Safety: The Cameras Tracking You Are a Security Nightmare [video] -- 2025-11-21
  244. Google cracked Apple's AirDrop and is adding it to Pixel phones -- 2025-11-21
  245. DOE gives Microsoft partner $1B loan to restart Three Mile Island reactor -- 2025-11-20
  246. Android Developer Verification Starts as Google Partially Retreats on Measures -- 2025-11-20
  247. [Editorial] https://www.linkedin.com/posts/avi-lumelsky-713111144_an-ai-powered-cyberattack-is-self-replicating-activity-7396569417549234177-n6ai -- 2025-11-19
  248. Native Sysmon functionality coming to Windows -- 2025-11-19
  249. BSD MAC LLM UI: Minimal, Auditable LLM Front End for Secure Environments -- 2025-11-18
  250. easy-oidc/easy-oidc -- 2025-11-18
  251. Disrupting the first reported AI-orchestrated cyber espionage campaign -- 2025-11-18
  252. The Challenge of Large File Checksums -- 2025-11-18
  253. Building A Smart Speaker Outside The Corporate Cloud -- 2025-11-18
  254. [Editorial] https://d1.awsstatic.com/onedam/marketing-channels/website/aws/en_US/whitepapers/compliance/AI-for-Security-and-Security-for-AI_Navigating-Opportunities-and-Challenges.pdf -- 2025-11-17
  255. [Editorial] https://www.oligo.security/blog/shadowmq-how-code-reuse-spread-critical-vulnerabilities-across-the-ai-ecosystem -- 2025-11-17
  256. [Editorial] https://www.linkedin.com/posts/helloamychang_death-by-a-thousand-prompts-open-model-vulnerability-activity-7392678891724861441-foCf/ -- 2025-11-17
  257. Data breach at Chinese firm reveals list of targets -- 2025-11-17
  258. [Editorial] https://thehackernews.com/2025/11/microsoft-uncovers-whisper-leak-attack.html -- 2025-11-14
  259. [Editorial] Web Authentication is Broken -- 2025-11-13
  260. Why a lot of people are getting hacked with government spyware -- 2025-11-13
  261. Project Idea: Using an AI face search to find data leakage in RAG source repositories. -- 2025-11-13
  262. meysam81/parse-dmarc -- 2025-11-13
  263. Beelzebub MCP: Securing AI Agents with Honeypot Functions, Prompt Injection Detection -- 2025-11-11
  264. Problem Uploading PDFs in Self hosted AI -- 2025-11-11
  265. openai/gpt-oss-safeguard-20b -- 2025-11-11
  266. funnyzak/reqtap -- 2025-11-10
  267. Operation Chargeback: 4.3M cardholders affected, EUR 300M in damages -- 2025-11-10
  268. Windows Update triggers BitLocker recovery on business PCs -- 2025-11-10
  269. Password to Louvre video surveillance system was 'Louvre', according to employee -- 2025-11-10
  270. [Research] Cross-Stage Vulnerabilities in Large Language Model Architectures -- 2025-11-07
  271. runZeroInc/runZeroHound -- 2025-11-07
  272. openai/gpt-oss-safeguard-120b -- 2025-11-07
  273. [Editorial] https://genai.owasp.org/resource/cheatsheet-a-practical-guide-for-securely-using-third-party-mcp-servers-1-0/ -- 2025-11-06
  274. schollz/e2ecp -- 2025-11-06
  275. alicanli1995/conform -- 2025-11-06
  276. [Editorial] https://www.linkedin.com/posts/gadievron_deep-dive-cursor-code-injection-runtime-activity-7391805842318077952-bRjD -- 2025-11-05
  277. [Editorial] Supply chain attacks -- 2025-11-03
  278. VSCode (Win10) + Claude Code: chrome-devtools-mcp keeps asking permissions — how to auto-allow? -- 2025-11-03
  279. schollz/share -- 2025-11-03
  280. FLOSS Weekly Episode 853: Hardware Addiction; Don’t Send Help -- 2025-11-03
  281. [Editorial] https://commsrisk.com/sms-blaster-and-imsi-catcher-news-from-lebanon-cambodia-switzerland-and-the-philippines/ -- 2025-11-03
  282. An Obscure Military Program Helps Local Cops Buy Armored Card and Spyware -- 2025-11-03
  283. mocred/spyder-osint -- 2025-11-02
  284. CISA and NSA share tips on securing Microsoft Exchange servers -- 2025-11-02
  285. DarkBitx/ICRev -- 2025-11-01
  286. dd1100/DiscordRAT -- 2025-11-01
  287. Police used Flock cameras to accuse a woman of theft, she had to prove innocence -- 2025-11-01
  288. [Editorial] https://www.npmjs.com/package/strange-loops -- 2025-10-31
  289. [Editorial] AIF? -- 2025-10-31
  290. p0dalirius/ShareHound -- 2025-10-31
  291. FTC: No, hashing still doesn't make your data anonymous -- 2025-10-31
  292. Tor Browser 15.0 -- 2025-10-31
  293. [Editorial] Breaking facial recognition -- 2025-10-30
  294. I am a rogue cloud GPU provider, how do I intercept your horny chats? -- 2025-10-30
  295. Connect your Google Drive, Gmail, and local files — while keeping everything private -- 2025-10-30
  296. Apple says US passport digital IDs are coming to Wallet 'soon' -- 2025-10-30
  297. [Editorial] https://tee.fail/ -- 2025-10-29
  298. Satellite Snooping Reveals Sensitive Unencrypted Data -- 2025-10-29
  299. LLMs becoming rogue AGIs—And What That Means -- 2025-10-27
  300. RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns -- 2025-10-27
  301. How can i training AI model to Pentest (Cyber) without restriction ? -- 2025-10-26
  302. SpaceX disables 2,500 Starlink terminals allegedly used by Asian scam centers -- 2025-10-26
  303. Xubuntu website hacked and served malware -- 2025-10-26
  304. The Great ADS1115 Pricing and Sourcing Mystery -- 2025-10-26
  305. How do you handle model licenses when distributing apps with embedded LLMs? -- 2025-10-25
  306. Foreign hackers breached a US nuclear weapons plant via SharePoint flaws -- 2025-10-25
  307. Hugging Face and VirusTotal collaborate to strengthen AI security -- 2025-10-25
  308. [Editorial] Browsers you can socially engineer -- 2025-10-24
  309. CVE-2025-23313: Critical Vulnerability in NVIDIA NeMo Framework Leads to Potential System Compromise - Ameeba Exploit Tracker -- 2025-10-24
  310. [Editorial] New web -- 2025-10-23
  311. ContextGuard – Open-source security monitoring for MCP servers -- 2025-10-23
  312. Gemini AI owners, please, I beg you, let me disable canvas permanently -- 2025-10-23
  313. We rewrote OpenFGA in pure Postgres -- 2025-10-22
  314. Ntfsplus: NTFS Filesystem Remake -- 2025-10-22
  315. [Editorial] https://www.linkedin.com/posts/mavlevin_aisecurity-zeroday-cybersecurity-activity-7386478715813330944-P9OP -- 2025-10-22
  316. Linux Capabilities Revisited -- 2025-10-22
  317. [Editorial] Asimov’s three laws — updated for the genAI age -- 2025-10-17
  318. Comparing Popular AI Evaluation Platforms for 2025 -- 2025-10-17
  319. I analyzed 200 e-commerce sites and found 73% of their traffic is fake -- 2025-10-17
  320. thand-io/agent -- 2025-10-17
  321. Attack Turns Mouse into Microphone -- 2025-10-17
  322. On Deepfake Voice Detection -- It's All in the Presentation -- 2025-10-17
  323. Google C2S-Scale 27B (based on Gemma) built with Yale generated a novel hypothesis about cancer cellular behavior - Model + resources are now on Hugging Face and GitHub -- 2025-10-16
  324. MrDevAnony/MyIP -- 2025-10-16
  325. Modern iOS Security Features – A Deep Dive into SPTM, TXM, and Exclaves -- 2025-10-16
  326. 2025 Component Abuse Challenge: Making A TTL Demultiplexer Sweat -- 2025-10-16
  327. Signed Backdoor Hiding in Plain Sight on Framework Devices -- 2025-10-15
  328. Three ways formally verified code can go wrong in practice -- 2025-10-15
  329. Jeep pushed software update that bricked all 2024 Wrangler 4xe models -- 2025-10-15
  330. junron/agar -- 2025-10-15
  331. A modern approach to preventing CSRF in Go -- 2025-10-15
  332. This Week in Security: ID Breaches, Code Smell, and Poetic Flows -- 2025-10-14
  333. I made a plugin to run LLMs on phones -- 2025-10-13
  334. 🚀 ToolNeuron Beta-4.5 — Offline & Privacy-First AI Hub for Android! -- 2025-10-13
  335. Emacs agent-shell (powered by ACP) -- 2025-10-13
  336. install package to open web ui gpt api env -- 2025-10-13
  337. Biasing issue with long_conversation_reminder -- 2025-10-12
  338. PSA: Always use a separate domain for user content -- 2025-10-12
  339. Major security breach at Austrian AI startup localmind.ai -- 2025-10-12
  340. Fighting Email Spam on Your Mail Server with LLMs — Privately -- 2025-10-12
  341. [Editorial] https://www.anthropic.com/research/small-samples-poison -- 2025-10-11
  342. [Editorial] https://www.linkedin.com/pulse/from-chatbot-operating-system-what-openais-next-move-means-leimer-ju18c -- 2025-10-11
  343. Rubygems.org AWS Root Access Event – September 2025 -- 2025-10-11
  344. Dark Patterns: Buying a Bahncard at Deutsche Bahn -- 2025-10-10
  345. ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls -- 2025-10-10
  346. Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts -- 2025-10-10
  347. Thank you Anthropic & this community! Our little side project just hit 1M visits and even made it on National TV! -- 2025-10-10
  348. THUDM/INFTY -- 2025-10-10
  349. Qwen3-VL-30B-A3B-Thinking GGUF with llama.cpp patch to run it -- 2025-10-10
  350. What and when 7900xtx is boosted? -- 2025-10-10
  351. Script to install a bunch of AI or Dev tools automatically.. what can I add to it or improve? -- 2025-10-10
  352. Qwen/Qwen3-VL-30B-A3B-Instruct -- 2025-10-10
  353. BenchVolt PD: USB PD Meets Benchtop Precision -- 2025-10-10
  354. [Editorial] Reminder that Prompt||GTFO #9 is today. -- 2025-10-09
  355. Breaking "Provably Correct" Leftpad -- 2025-10-09
  356. Provable scaling laws of feature emergence from learning dynamics of grokking -- 2025-10-09
  357. SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications -- 2025-10-09
  358. kyomber/CVE-2025-8088 -- 2025-10-08
  359. This Week in Security: CVSS 0, Chwoot, and Not in the Threat Model -- 2025-10-08
  360. [Editorial] https://www.linkedin.com/posts/dmitry-kurbatov_5g-satellitetechnology-cybersecurity-activity-7381247864624148480-6_4n -- 2025-10-07
  361. Signal Protocol and Post-Quantum Ratchets -- 2025-10-07
  362. Unitree Humanoid Robot Exploit Looks Like a Bad One -- 2025-10-07
  363. [Editorial] https://www.linkedin.com/posts/albertochierici_lol-i-cant-stop-thinking-about-this-we-activity-7379840898626502656-bUYZ -- 2025-10-03
  364. Vyzer9/Valkan -- 2025-10-03
  365. Bypassing TLS Certificate Validation with Ld_preload -- 2025-10-03
  366. 1652933138/eth-address-poisoning-tool -- 2025-09-30
  367. Upgrade to Kernel 6.16.9 solves 15.5GB Stix Halo memory limitation -- 2025-09-30
  368. Seeking Advice: Best Model + Framework for Max Tokens/sec on Dual L40S (Testing Rig) -- 2025-09-30
  369. [Editorial] Goalie MCP, better search -- 2025-09-29
  370. GrapheneOS Release 2025092700 -- 2025-09-29
  371. MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data -- 2025-09-29
  372. There's a bug in the automatic review system for 'designing weapons'... I was coding a gun animation for my browser game. -- 2025-09-27
  373. Scammers using artifacts for phishing like sites? -- 2025-09-27
  374. Supermicro server motherboards can be infected with unremovable malware -- 2025-09-27
  375. ChatControl: EU wants to scan all private messages, even in encrypted apps -- 2025-09-27
  376. PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models -- 2025-09-25
  377. RX 7700 launched with 2560 cores (relatively few) and 16GB memory with 624 GB/s bandwidth (relatively high) -- 2025-09-25
  378. BitsByWill/ksmbd-n-day -- 2025-09-25
  379. Checking that functions are constant time with Valgrind -- 2025-09-25
  380. Fine-grained HTTP filtering for Claude Code -- 2025-09-25
  381. Haasoscope Pro: Open-Everything 2 GHz USB Oscilloscope -- 2025-09-25
  382. OpenSSF: Best Practices -- 2025-09-25
  383. luongngocminh/check-npm-supplychain-2025 -- 2025-09-25
  384. "Bypassing" Cloudflare's Turnstile Captcha with Thermoptic -- 2025-09-24
  385. Robot Balances Ball On A Plate -- 2025-09-24
  386. caarlos0/pinata -- 2025-09-24
  387. A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code -- 2025-09-24
  388. Advice on building an enterprise-scale, privacy-first conversational assistant (local LLMs with Ollama vs fine-tuning) -- 2025-09-22
  389. Pnpm has a new setting to stave off supply chain attacks -- 2025-09-22
  390. A Deep Dive on Creepy Cameras -- 2025-09-22
  391. [Editorial] A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks -- 2025-09-21
  392. Claude Code native subagents vs. Claude Flow vs. BMAD -- 2025-09-21
  393. Hallucination in LLM-Based Code Generation: An Automotive Case Study -- 2025-09-21
  394. GGUF security concerns -- 2025-09-20
  395. Democratizing AI Safety with RiskRubric.ai -- 2025-09-20
  396. What Facebook's Memcache Taught Me About Systems Thinking -- 2025-09-20
  397. Linus Torvalds Guitar Pedal Project -- 2025-09-20
  398. Alex Karp Insists Palantir Doesn't Spy on Americans. Here's What He's Not Saying -- 2025-09-20
  399. Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes -- 2025-09-20
  400. phishingclub/phishingclub -- 2025-09-19
  401. New Phoenix attack bypasses Rowhammer defenses in DDR5 memory -- 2025-09-19
  402. This Week in Security: The Shai-Hulud Worm, ShadowLeak, and Inside the Great Firewall -- 2025-09-19
  403. Autonomous Pen testing AI. -- 2025-09-19
  404. SmartCoder-R1: Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization -- 2025-09-17
  405. Shai-Hulud malware attack: Tinycolor and over 40 NPM packages compromised -- 2025-09-17
  406. Oh no, not again a meditation on NPM supply chain attacks -- 2025-09-17
  407. Fix AI pipeline bugs before they hit your local stack: a semantic firewall + grandma clinic (beginner friendly, MIT) -- 2025-09-17
  408. [Editorial] Villager -- 2025-09-16
  409. Update: we got our revenge and now beat Deepmind, Microsoft, Zhipu AI and Alibaba -- 2025-09-16
  410. MacOS silicon - llama.cpp vs mlx-lm -- 2025-09-15
  411. NT OS Kernel Information Disclosure Vulnerability -- 2025-09-15
  412. [Editorial] Enterprise Security -- 2025-09-14
  413. Crates.io phishing attempt -- 2025-09-14
  414. [OSS] Beelzebub — “Canary tools” for AI Agents via MCP -- 2025-09-12
  415. Defeating Nondeterminism in LLM Inference -- 2025-09-12
  416. This Week in Security: NPM, Kerbroasting, and The Rest of the Story -- 2025-09-12
  417. How the “Kim” dump exposed North Korea's credential theft playbook -- 2025-09-09
  418. Further Adventures in Colorimeter Hacking -- 2025-09-09
  419. I made local RAG, web search, and voice mode on iPhones completely open source, private, and free -- 2025-09-08
  420. jwest33/jam_model_memory -- 2025-09-08
  421. In-Browser AI: WebLLM + WASM + WebWorkers -- 2025-09-06
  422. FluidAudio, a local-first Swift SDK for real-time speaker diarization, ASR & audio processing on iOS/MacOS -- 2025-09-06
  423. Is there a way to have models load in to vram quicker, or stay alive without persisting in vram? Or are there alternatives for fast models? -- 2025-09-06
  424. A simple zsh function to bring “Copilot Inline Chat for Terminal” to any shell -- 2025-09-06
  425. iblameandrew/local-deepsearch-academic -- 2025-09-05
  426. From Libraries to Schools: Why Organizations Should Install Privacy Badger -- 2025-09-05
  427. Empirical Evaluation of Concept Drift in ML-Based Android Malware Detection -- 2025-09-05
  428. auth0/auth0-customer-detections -- 2025-09-05
  429. pwnfuzz/diffrays -- 2025-09-04
  430. Chromium Hardening Guide -- 2025-09-04
  431. roomkangali/dursgo -- 2025-09-04
  432. “Grokking”: Scammers use Grok to surface malicious links hidden in ads -- 2025-09-04
  433. Authenticate Thyself -- 2025-09-04
  434. [Editorial] LLM vulnerable to social engineering -- 2025-09-03
  435. [Editorial] Indirect Prompt Injection Attacks Against LLM Assistants -- 2025-09-03
  436. [Editorial] AI Apocalypse -- 2025-09-03
  437. First known AI-powered ransomware. Ollama API + gpt-oss-20b -- 2025-09-03
  438. Using JWT to establish a trusted context for Row Level Security -- 2025-09-02
  439. Web Bot Auth -- 2025-09-02
  440. Anthropic will train Claude on consumer chats unless opted out by Sept 28; toggle is on by default -- 2025-09-02
  441. Coral-Protocol/Anemoi -- 2025-09-01
  442. After researchers unmasked a prolific SMS scammer, a new operation has emerged -- 2025-09-01
  443. Silent No More: Open-Source Fix for Mic Mishaps -- 2025-09-01
  444. How to reliably detect cross-listed job ads across multiple sites? -- 2025-09-01
  445. gmh5225/aug_cleaner -- 2025-08-31
  446. HexRaysSA/ida-domain -- 2025-08-31
  447. Nx compromised: malware uses Claude code CLI to explore the filesystem -- 2025-08-31
  448. AI Detection in 2025: What Actually Triggers Flags (and How to Write Like a Human) -- 2025-08-30
  449. facebookincubator/pces -- 2025-08-29
  450. Google Debuts Device-Bound Session Credentials Against Session Hijacking -- 2025-08-29
  451. Treasury Announces Federal Govt Will Phase Out Paper Checks on September 30th -- 2025-08-29
  452. Bearer token keeps getting forgotten - somehow -- 2025-08-29
  453. Open-source experiment: LLM-Ripper -- 2025-08-28
  454. MorDavid/vCenterHound -- 2025-08-28
  455. A failure of security systems at PayPal is causing concern for German banks -- 2025-08-28
  456. Battery Repair By Reverse Engineering -- 2025-08-28
  457. A hacker used AI to automate an 'unprecedented' cybercrime spree, Anthropic says -- 2025-08-28
  458. [Editorial] AI and security tools. -- 2025-08-27
  459. [Editorial] AI, cve, auto exploitation -- 2025-08-26
  460. [Editorial] Promptware Attacks Against LLM-Powered Assistants -- 2025-08-26
  461. [Editorial] AI portscan -- 2025-08-26
  462. Prompt Obfuscation -- 2025-08-26
  463. synacktiv/GroupPolicyBackdoor -- 2025-08-26
  464. DavidBuchanan314/anubis_offload -- 2025-08-26
  465. Developer sentenced to prison for activating “kill switch” to avenge his firing -- 2025-08-25
  466. How to Stop Zeus from Toasting Your Pi -- 2025-08-25
  467. superfashi/pwnbot-ng -- 2025-08-25
  468. Automated microgreens mini-farm ran by Claude Code -- 2025-08-25
  469. PurinNyova/Image-Detection-Bypass-Utility -- 2025-08-25
  470. [Editorial] Latest phrack -- 2025-08-24
  471. I built an AI workspace where you can create custom apps without coding - here's the early beta -- 2025-08-24
  472. I built real-time course correction for Claude Code... and it's also a Tamagotchi -- 2025-08-24
  473. I Hacked India's Biggest Dating App (They Offered Me a $100 Gift Card) -- 2025-08-24
  474. Roll Your Own SSB Receiver -- 2025-08-24
  475. Rubby2001/Rshell---A-Cross-Platform-C2 -- 2025-08-23
  476. Cloudflare incident on August 21, 2025 -- 2025-08-23
  477. Intel Outside: Hacking every Intel employee and various internal websites -- 2025-08-22
  478. On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions -- 2025-08-22
  479. Looking for datasets/tools for testing document forgery detection in medical claims -- 2025-08-22
  480. [Editorial] Seemingly Conscious AI... -- 2025-08-22
  481. AGENTS.md – Open format for guiding coding agents -- 2025-08-21
  482. turtacn/kubestack-ai -- 2025-08-21
  483. Critical Cache Poisoning Vulnerability in Dnsmasq -- 2025-08-21
  484. Security Researchers Find XZ Utils Backdoored Debian Images on Docker Hub -- 2025-08-20
  485. Open Source Lithium-Titanate Battery Management System -- 2025-08-20
  486. Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty -- 2025-08-20
  487. [Editorial] XBOW vs HackerOne, Flawless victory! -- 2025-08-19
  488. GPT-5 doubles performance in offensive security benchmark -- 2025-08-19
  489. Solving the Nostr web clients attack vector -- 2025-08-18
  490. Trump-Putin Summit Documents Left in Hotel Printer -- 2025-08-18
  491. scosman/secret_share -- 2025-08-16
  492. Has anyone successfully connected Open WebUI to the Microsoft Graph API? -- 2025-08-16
  493. A New List Reveals Top Websites Meta Is Scraping of Copyrighted Content -- 2025-08-15
  494. VECERTUSA/DarkForumCTI -- 2025-08-15
  495. 0x4D31/finch -- 2025-08-14
  496. GitHub Copilot: Remote code execution via prompt injection (CVE-2025-53773) -- 2025-08-14
  497. The WHY 2025 Badge and its 18650s -- 2025-08-14
  498. [Editorial] New Red Team's Networking Techniques -- 2025-08-13
  499. [Editorial] GLM-4.5, enterprise use -- 2025-08-13
  500. GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface -- 2025-08-13
  501. Nonescape: SOTA AI-Image Detection Model (Open-Source) -- 2025-08-12
  502. Activation-Guided Local Editing for Jailbreaking Attacks -- 2025-08-12
  503. Anti-competitive practices masquerading as security is a dangerous pattern -- 2025-08-11
  504. Doctors horrified after Google's healthcare AI makes up body part -- 2025-08-11
  505. This Week in Security: Perplexity v Cloudflare, GreedyBear, and HashiCorp -- 2025-08-11
  506. gpt-oss jailbreak workflow -- 2025-08-11
  507. GPT-5 removed logprob support from the API - technical breakdown and implications -- 2025-08-11
  508. A model for pure text continuation (not chirpy little Q&A assistant)? -- 2025-08-11
  509. One File, Six Formats: Just Change The Extension -- 2025-08-10
  510. VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation -- 2025-08-10
  511. Wukong Framework for Not Safe For Work Detection in Text-to-Image systems -- 2025-08-10
  512. Automating Steering for Safe Multimodal Large Language Models -- 2025-08-10
  513. LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning -- 2025-08-10
  514. [Editorial] microsoft's copilot studio agents hijacked -- 2025-08-09
  515. I see people rushing to GLM Air GGUF's on this repo - what does this warning usually mean? I haven't seen a model flagged since we passed around pickled weights -- 2025-08-09
  516. Jepsen: Capela dda5892 -- 2025-08-09
  517. A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models -- 2025-08-09
  518. n0xa/SecKC-MHN-Globe -- 2025-08-08
  519. LLM-Based Identification of Infostealer Infection Vectors from Screenshots: The Case of Aurora -- 2025-08-08
  520. Reason ex Machina: Jailbreaking LLMs by Squeezing Their Brains | xayan.nu -- 2025-08-08
  521. [Editorial] Open source GUI for Claude Code -- 2025-08-08
  522. DoubleAgents: Fine-tuning LLMs for Covert Malicious Tool Calls -- 2025-08-08
  523. Hey folks, I’m one of the contributors to Bifrost, and we just launched it on Product Hunt -- 2025-08-08
  524. Funny but annoying time bug -- 2025-08-08
  525. A free goldmine of tutorials for the components you need to create production-level agents Extensive open source resource with tutorials for creating robust AI agents -- 2025-08-08
  526. What to do with a NVIDIA Tesla V100S 32GB GPU -- 2025-08-07
  527. dsekz/chrome-x-browser-validation-header -- 2025-08-07
  528. MorDavid/BruteForceAI -- 2025-08-07
  529. Show HN: Aura – Like robots.txt, but for AI actions -- 2025-08-07
  530. I built a GitHub scanner that automatically discovers AI tools using a new .awesome-ai.md standard I created -- 2025-08-07
  531. "Private ChatGPT conversations show up on Search Engine, leaving internet users shocked again" -- 2025-08-07
  532. I made an AI calorie tracker - it is 100% free and better -- 2025-08-07
  533. [Editorial] NIST SP 800-63-4 -- 2025-08-05
  534. I tried living on IPv6 for a day, and here's what happened -- 2025-08-05
  535. [Editorial] Agentic security testing -- 2025-08-04
  536. [Editorial] ML System Design Case Studies Repository -- 2025-08-04
  537. I built a GitHub scanner that automatically discovers your AI tools using a new .awesome-ai.md standard I created -- 2025-08-04
  538. [Editorial] Agentic AI security -- 2025-08-03
  539. Amazon's AI Coding Revealed a Dirty Little Secret -- 2025-08-02
  540. On the Interaction of Compressibility and Adversarial Robustness -- 2025-08-02
  541. bytillo/spyder-osint -- 2025-08-01
  542. Secure boot certificate rollover is real but probably won't hurt you -- 2025-08-01
  543. 2025 One Hertz Challenge: RPI TinynumberHat9 -- 2025-08-01
  544. [Editorial] AI in hostile environments... -- 2025-08-01
  545. leesh3288/CVE-2025-32023 -- 2025-08-01
  546. In search of riches, hackers plant 4G-enabled Raspberry Pi in bank network -- 2025-08-01
  547. Debugging the Pixel 8 kernel via KGDB -- 2025-07-31
  548. zerolabnet/SSAntifilter -- 2025-07-30
  549. Playing with more user-friendly methods for multi-factor authentication -- 2025-07-30
  550. We just open sourced NeuralAgent: The AI Agent That Lives On Your Desktop and Uses It Like You Do! -- 2025-07-30
  551. Help with UnifyAI – Setting Up Local LLMs and UI Integration -- 2025-07-30
  552. PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models -- 2025-07-29
  553. Guide to PDF security -- 2025-07-28
  554. MetaMask extension bug causes 100s of GBs of extraneous data to be written -- 2025-07-28
  555. Commodore 64 on New FPGA -- 2025-07-28
  556. Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems -- 2025-07-27
  557. Shanghai AI Lab Just Released a Massive 97-Page Safety Evaluation of Frontier AI Models - Here Are the Most Concerning Findings -- 2025-07-27
  558. FreeBSD 15.0 Aims to Have a KDE Desktop Install Option -- 2025-07-27
  559. A Different Way to Think about Plane Fitting -- 2025-07-27
  560. Engrave a Cylinder Without a Rotary Attachment? No Problem! -- 2025-07-27
  561. India: Income Tax Bill allows officials to forcibly access social media, email -- 2025-07-25
  562. muyuanlove/sensitive_info_extractor -- 2025-07-24
  563. Wordle-like game using your photos and on-device Small Language Models (SLMs) -- 2025-07-24
  564. FreeBSD 15's installer to gain option to install a full KDE Plasma desktop -- 2025-07-24
  565. Spanish police arrest five over $542M crypto investment scheme -- 2025-07-24
  566. A Spectrophotometer Jailbreak to Resolve Colorful Disputes -- 2025-07-24
  567. Chess Llama - Training a tiny Llama model to play chess -- 2025-07-23
  568. Reverse Engineering a ‘Tony’ 6502-based Mini Arcade Machine -- 2025-07-23
  569. ezozu/SignalForge -- 2025-07-23
  570. Warashi/cage -- 2025-07-22
  571. The Most Powerful Server Embiggens a Bit with Power11 -- 2025-07-22
  572. Vintage Hardware Find Includes Time Capsule of Data -- 2025-07-22
  573. rip-zoyo/orbit-tls -- 2025-07-22
  574. Claude is IN the files. -- 2025-07-21
  575. Bitcoin Devs Float Proposal to Freeze Quantum-Vulnerable Addresses -- 2025-07-21
  576. OpenSCAD: The Programmers Solid 3D CAD Modeller -- 2025-07-21
  577. Software Defined Retro ROMs -- 2025-07-21
  578. Arc Virtual Cell Challenge: A Primer -- 2025-07-21
  579. BlueFalconHD/apple_generative_model_safety_decrypted -- 2025-07-19
  580. A Vulnerable Simulator for Drone Penetration Testing -- 2025-07-19
  581. yegors/co-atc -- 2025-07-19
  582. Defense Department to begin using Grok -- 2025-07-18
  583. Claude deleted my whole repository -- 2025-07-17
  584. Japan Achieves World Record 1.02 Petabits per Second Internet Speed -- 2025-07-15
  585. Jcorp Nomad: ESP32-S3 Offline Media Server in a Thumbdrive -- 2025-07-15
  586. We built pinpointed citations for AI answers — works with PDFs, Excel, CSV, Docx & more -- 2025-07-15
  587. Ollama retaining history? -- 2025-07-15
  588. Does AIStudio's Gemini 2.5 Pro log and train data? -- 2025-07-15
  589. TheManticoreProject/LDAPWordlistHarvester -- 2025-07-14
  590. Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure -- 2025-07-14
  591. What impressive (borderline creepy) local AI tools can I run now that everything is local? -- 2025-07-12
  592. ScreenEnv: Deploy your full stack Desktop Agent -- 2025-07-12
  593. Running OpenWebUI Without RAG: Faster Web Search & Document Upload -- 2025-07-12
  594. Probing Evaluation Awareness of Language Models -- 2025-07-11
  595. O2 VoLTE: locating any customer with a phone call -- 2025-07-09
  596. This Week in Security: Anthropic, Coinbase, and Oops Hunting -- 2025-07-08
  597. How to think about ownership of my personal AI system -- 2025-07-08
  598. Wallbleed: A Memory Disclosure Vulnerability in the Great Firewall of China -- 2025-07-05
  599. 0-Pierced Triangles within a Poisson Overlay -- 2025-07-05
  600. 1000 days of lowest frequency emission from the low-luminosity GRB 171205A -- 2025-07-05
  601. CAI: An Open, Bug Bounty-Ready Cybersecurity AI -- 2025-07-04
  602. How realistic is it to run a media site entirely on AI-generated code with no developers? -- 2025-07-03
  603. Hack of SEC's Edgar System Exposed Flaws in US Financial Security -- 2025-06-29
  604. $^{100}$Mo-enriched Li$_2$MoO$_4$ scintillating bolometers for $0\nu 2\beta$ decay search: from LUMINEU to CUPID-0/Mo projects -- 2025-06-29
  605. chainguard-dev/kaniko -- 2025-06-26
  606. nushell/nushell -- 2025-06-26
  607. Washington Post's Privacy Tip: Stop Using Chrome, Delete Meta Apps (and Yandex) -- 2025-06-26
  608. martinbowling/thinkchain -- 2025-06-25
  609. WireGuard vanity keygen -- 2025-06-25
  610. zeptoforth: A not-so-small Forth for ARM Cortex-M -- 2025-06-25
  611. AI in my plasma physics research didn’t go the way I expected -- 2025-06-23
  612. open-webui/mcpo -- 2025-06-23
  613. Built a fully local Whisper + pyannote stack to replace Otter. Full diarisation, transcripts & summaries on GPU. -- 2025-06-23
  614. MiniMax latest open-sourcing LLM, MiniMax-M1 — setting new standards in long-context reasoning,m -- 2025-06-23
  615. Run qwen 30b-a3b on Android local with Alibaba MNN Chat -- 2025-06-23
  616. A new PDF translation tool -- 2025-06-23
  617. What Really Happens When You Ask a Cursor a Question with GitHub MCP Integrated -- 2025-06-23
  618. [Q] How to Speed Up Mistral 7B Inference in LM Studio? 31s/Chunk on RTX 3070 -- 2025-06-23
  619. Cyber security guys are about to become very on demand in the coming few years -- 2025-06-23
  620. The first big AI disaster is yet to happen -- 2025-06-23
  621. Trading with Claude, and writing your own MCP server -- 2025-06-23
  622. Ecne AI Podcast Generator - Update -- 2025-06-23
  623. Help me decide on hardware for LLMs -- 2025-06-23
  624. Java Virtual Threads Ate My Memory: A Web Crawler's Tale of Speed vs. Memory -- 2025-06-20
  625. Show HN: Zeekstd – Rust Implementation of the ZSTD Seekable Format -- 2025-06-20
  626. n8n-io/n8n -- 2025-06-20
  627. kn0x0x/CVE-2025-32756-POC -- 2025-06-17
  628. Magic Leap One Bootloader Exploit -- 2025-06-17
  629. Take9 Won't Improve Cybersecurity -- 2025-06-17
  630. Authy corrupted my 2FA backup and all I got was this lousy blogpost -- 2025-06-16
  631. rusjoan/streamcrypt -- 2025-06-12
  632. tang-bd/fuse-dit -- 2025-06-12
  633. Show HN: 3DGS implementation in Nvidia Warp: clean, minimal, runs on CPU and GPU -- 2025-06-12
  634. 0.75 atoms improve the clock signal of 10,000 atoms -- 2025-06-12
  635. Clipjacking: Hacked by copying text – Clickjacking but better -- 2025-06-11
  636. 0.52 V-mm ITO-based Mach-Zehnder Modulator in Silicon Photonics -- 2025-06-10
  637. Russia's Pravda Network: AI-Driven Disinformation on a Global Scale -- 2025-06-10
  638. Show HN: Forge – Secure, Multi-Tenant GitHub Actions Runners on K8s or EC2 -- 2025-06-09
  639. Weaponizing Dependabot: Pwn Request at its finest -- 2025-06-08
  640. Experts -- 2025-06-08
  641. Claude 4 -- 2025-06-07
  642. Claude Code is now available to Pro plans -- 2025-06-07
  643. al-sultani/prokzee -- 2025-06-07
  644. stripedvitro/utilities -- 2025-06-07
  645. Show HN: I built an AI Agent that uses the iPhone -- 2025-06-04
  646. PipesHub - Open Source Enterprise Search Platform(Generative-AI Powered) -- 2025-06-04
  647. A Privacy-Focused Perplexity That Runs Locally on Your Phone -- 2025-06-04
  648. RL Based Sales Conversion - I Just built a PyPI package -- 2025-06-04
  649. Is a VectorDB the best solution for this? -- 2025-06-04
  650. Finetuning or running the new gemma 3n models locally? -- 2025-06-04
  651. Automate Your CSV Analysis with AI Agents – CrewAI + Ollama -- 2025-06-04
  652. A simple guide to downloading models using Open WebUI & Ollama — no stress, just steps -- 2025-06-04
  653. what's the best ai model for large refactors? -- 2025-06-04
  654. Show HN: Wetlands – a lightweight Python library for managing Conda environments -- 2025-06-04
  655. Deadlocks in Go: the dark side of concurrency (2021) -- 2025-06-04
  656. ban6cat6/aparecium -- 2025-06-03
  657. 0-Gaps on 3D Digital Curves -- 2025-06-03
  658. I'm building a Self-Hosted Alternative to OpenAI Code Interpreter, E2B -- 2025-06-01
  659. Giving Qwen 3 0.6B a Toolbelt in the form of MCP Support, Running Locally in Your Browser with Adjustable Thinking! -- 2025-06-01
  660. Turning my PC into a headless AI workstation -- 2025-06-01
  661. Bind tools to a model for use with Ollama and OpenWebUI -- 2025-06-01
  662. I know it's -- 2025-06-01
  663. We believe the future of AI is local, private, and personalized. -- 2025-06-01
  664. image search and query with natural language that runs on the local machine -- 2025-06-01
  665. What's the verdict on the new OpenAI Codex? -- how's code quality? Comparing to Cursor? -- 2025-06-01
  666. MCP explained without hype or fluff -- 2025-06-01
  667. Augmented Coding: Better with Principles -- 2025-06-01
  668. Best open source model for enterprise conversational support agent - worth it? -- 2025-06-01
  669. Speed-up VLLM server boot -- 2025-06-01
  670. An Almost Pointless Exercise in GPU Optimization -- 2025-05-31
  671. The Windows Registry Adventure #7: Attack surface analysis -- 2025-05-31
  672. 'He spent thousands': how a bank team tries to rescue scam victims -- 2025-05-31
  673. Octoberfest7/zip_smuggling -- 2025-05-30
  674. Silencing Firefox's Chattiness for Web App Testing -- 2025-05-30
  675. stacklok/toolhive -- 2025-05-29
  676. botirk38/semanticcache -- 2025-05-29
  677. Proton threatens to quit Switzerland over new surveillance law -- 2025-05-28
  678. jinn091/go-form-parser -- 2025-05-28
  679. doganarif/GoVisual -- 2025-05-28