OpenAI AI models exploited zero-days to reach Hugging Face in benchmark testSecurity Affairs·Jul 22, 08:52 UTC · Jul 22, 2026Exploit / PoC60
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat BenchmarkThe Hacker News·Jul 22, 20:30 UTC · Jul 22, 2026Exploit / PoC60
Researchers say AI just broke every benchmark for autonomous cyber capabilityCyberScoop·May 13, 22:29 UTC · May 13, 2026Exploit / PoC in the wild60
OpenAI's Next AI Model Astra Shows Cyber Performance Strong Enough to Trigger PauseThe Hacker News·Aug 10, 05:50 UTC · Aug 10, 2026Exploit / PoC160
More on the OpenAI Agent's Attack on Hugging FaceSchneier on Security·Aug 3, 17:03 UTC · Aug 3, 2026Exploit / PoC60
Week in review: Firmware-level Android backdoor found on tablets, Dell zero-day exploited since 2024Help Net Security·Feb 22, 00:00 UTC · Feb 22, 2026Exploit / PoC in the wildCVE-2026-2441CVE-2026-22769CVE-2026-2329+1 CVEs60
Zen-AI-Pentest: Open-source AI-powered penetration testing frameworkHelp Net Security·Feb 11, 00:00 UTC · Feb 11, 2026Exploit / PoC45
OpenAI Pauses Astra Model Over Critical Cybersecurity Risk ConcernsSecurity Affairs·Aug 10, 11:16 UTC · Aug 10, 2026Exploit / PoC160
NVIDIA Forms 37-Member Open Secure AI Alliance and OpenThe Hacker News·Jul 27, 18:10 UTC · Jul 27, 2026Exploit / PoC60
OpenAI says model test was behind Hugging Face hackCyberScoop·Jul 21, 22:39 UTC · Jul 21, 2026Exploit / PoC in the wild60
Anthropic's new AI model finds and exploits zero-days across every major OS and browserHelp Net Security·Jun 19, 12:14 UTC · Jun 19, 2026Exploit / PoC in the wildCVE-2026-474760
Trump administration releases scaledCyberScoop·Jun 3, 00:37 UTC · Jun 3, 2026Exploit / PoC in the wild60
⚡ Weekly Recap: Fortinet Exploited, China's AI Hacks, PhaaS Empire Falls & MoreThe Hacker News·Nov 17, 12:37 UTC · Nov 17, 2025Exploit / PoC in the wildCVE-2025-64446CVE-2025-64740CVE-2025-64741+24 CVEs60
Nvidia chips become the first GPUs to fall to Rowhammer bitArs Technica · Security·Jul 15, 00:00 UTC · Jul 15, 2025Exploit / PoC45
Google hopes its experimental AI model can unearth new security use casesCyberScoop·Apr 8, 01:07 UTC · Apr 8, 2025Exploit / PoC in the wild60
Tanium delivers autonomous controls that mitigate risk and maintain operational resiliencyHelp Net Security·Nov 19, 00:00 UTC · Nov 19, 2024Exploit / PoC60
Week in review: Microsoft fixes two exploited zero-days, SOC teams are losing trust in security toolsHelp Net Security·Oct 13, 00:00 UTC · Oct 13, 2024Exploit / PoC in the wildCVE-2024-43573CVE-2024-43572CVE-2024-9680+5 CVEs60
Tanium strengthens threat identification capabilities and enhances endpoint reachHelp Net Security·Jun 23, 00:00 UTC · Jun 23, 2023Exploit / PoC60
Runecast announces new capabilities to simplify Kubernetes security and speed up operationsHelp Net Security·Jul 26, 00:00 UTC · Jul 26, 2022Exploit / PoC60
E-Commerce alliance pushes cyber audits for vendorsCyberScoop·Nov 21, 15:29 UTC · Nov 21, 2016Exploit / PoC in the wild60
Cloud Security Alliance issues IoT security guideCyberScoop·Oct 11, 14:48 UTC · Oct 11, 2016Exploit / PoC in the wild60
Big tech companies unite to vet vendor cybersecurityCyberScoop·Sep 16, 17:00 UTC · Sep 16, 2016Exploit / PoC in the wild60
GPT-5.6-Cyber refuses security researchers’ requests far less oftenHelp Net Security·Aug 11, 00:00 UTC · Aug 11, 2026Exploit / PoCCVE-2026-1590360
AI-Assisted HTTP Terminator Finds Novel HTTP Desync Techniques and Apache ZeroThe Hacker News·Aug 7, 11:25 UTC · Aug 7, 2026Exploit / PoCCVE-2026-6307860
OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face BreachThe Hacker News·Aug 1, 05:20 UTC · Aug 1, 2026Exploit / PoC60
AI agents are changing where cybersecurity seed funding landsHelp Net Security·Jul 31, 00:00 UTC · Jul 31, 2026Exploit / PoC60
Supply chain challenges loom large in quantum race, White House official saysCyberScoop·Jul 29, 20:22 UTC · Jul 29, 2026Exploit / PoC in the wild60
Microsoft Says New Cybersecurity AI Model Helps MDASH Score 95.95% at Half the CostThe Hacker News·Jul 28, 09:21 UTC · Jul 28, 2026Exploit / PoC45
Researcher Says AI Helped Develop Linux TrafficThe Hacker News·Jul 28, 08:04 UTC · Jul 28, 2026Exploit / PoC in the wildCVE-2026-5326460
⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and MoreThe Hacker News·Jul 28, 05:26 UTC · Jul 28, 2026Exploit / PoC in the wildCVE-2026-16232CVE-2025-66376CVE-2026-54121+52 CVEs60
Microsoft debuts AI cybersecurity offerings as competition heats upCyberScoop·Jul 27, 23:47 UTC · Jul 27, 2026Exploit / PoC60
OpenAI Claims Its AI Models Went Rogue and Hacked Another CompanyInfosecurity Magazine·Jul 22, 11:40 UTC · Jul 22, 2026Exploit / PoC60
New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker CommandsThe Hacker News·Jul 15, 00:00 UTC · Jul 15, 2026Exploit / PoCCVE-2025-32711150
Anthropic's new model is Mythos on a leashCyberScoop·Jun 9, 19:46 UTC · Jun 9, 2026Exploit / PoC in the wild60
UK spy chief labels AI ‘unstoppable force’ with offensive, defensive ramifications for cyberspaceCyberScoop·May 27, 19:07 UTC · May 27, 2026Exploit / PoC in the wild60
White House charts new course for federal agencies and cybersecurity loggingCyberScoop·May 26, 19:09 UTC · May 26, 2026Exploit / PoC in the wild60
Anthropic: Mythos finds more than 10,000 software flaws in first monthCyberScoop·May 26, 15:15 UTC · May 26, 2026Exploit / PoC in the wild60
The readiness paradox: Why a false sense of cyber confidence is becoming a liabilityCyberScoop·May 21, 10:00 UTC · May 21, 2026Exploit / PoC in the wild60