New research finds that Claude breaks bad if you teach it to cheatCyberScoop·Nov 24, 22:41 UTC · Nov 24, 2025Exploit / PoC in the wild60
OpenAI AI models exploited zero-days to reach Hugging Face in benchmark testSecurity Affairs·Jul 22, 08:52 UTC · Jul 22, 2026Exploit / PoC60
Week in review: Windows zero-day exploit leaked, Patch Tuesday forecastHelp Net Security·Apr 12, 00:00 UTC · Apr 12, 2026Exploit / PoC in the wildCVE-2026-34197160
Google hopes its experimental AI model can unearth new security use casesCyberScoop·Apr 8, 01:07 UTC · Apr 8, 2025Exploit / PoC in the wild60
Tech experts recommend full steam ahead on US export controls for AICyberScoop·Apr 8, 20:42 UTC · Apr 8, 2025Exploit / PoC in the wild60
Week in review: WSUS vulnerability exploited to drop Skuld infostealer, PoC for BIND 9 DNS flaw publishedHelp Net Security·Nov 2, 00:00 UTC · Nov 2, 2025Exploit / PoCCVE-2025-2783CVE-2025-40778CVE-2025-59287+1 CVEs160
Google Makes CodeMender Available as Managed AI Security AgentInfosecurity Magazine·Jul 22, 10:30 UTC · Jul 22, 2026Exploit / PoC60
Beyond Acceleration and Automation: How AI + Intelligence Changes Cyber DefenseRecorded Future·May 14, 00:00 UTC · May 14, 2026Exploit / PoC in the wild60
Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, OpenThe Hacker News·Jun 9, 11:59 UTC · Jun 9, 2026Exploit / PoC in the wildCVE-2026-39987CVE-2026-31431CVE-2026-43284+1 CVEs160
Autonomous AI-driven worm can reason its way through corporate networksHelp Net Security·Jun 3, 00:00 UTC · Jun 3, 2026Exploit / PoC in the wild60
White House accuses Chinese company of distilling Anthropic’s FableCyberScoop·Jul 22, 16:45 UTC · Jul 22, 2026Exploit / PoC in the wild60
White House cyber official: identity security matters more than ever in the age of AICyberScoop·May 14, 20:15 UTC · May 14, 2026Exploit / PoC in the wild60
Rein Security launches to provide protection inside application production environmentsHelp Net Security·Feb 2, 12:24 UTC · Feb 2, 2026Exploit / PoC in the wild60
Tech Industry Bids to Tackle CyberInfosecurity Magazine·Mar 29, 10:30 UTC · Mar 29, 2023Exploit / PoC60
Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber SafeguardsThe Hacker News·Jun 10, 07:37 UTC · Jun 10, 2026Exploit / PoCCVE-2026-4747160
AI chatbots want your geolocation data. Privacy experts say beware.CyberScoop·Jun 8, 20:46 UTC · Jun 8, 2023Exploit / PoC in the wild60
AI’s constant patching treadmill can be a security problemCyberScoop·Jun 17, 22:36 UTC · Jun 17, 2026Exploit / PoC in the wild60
Semgrep Multimodal brings AI reasoning and rule-based analysis to code securityHelp Net Security·Mar 20, 00:00 UTC · Mar 20, 2026Exploit / PoC160
Anthropic's Claude Mythos Finds Thousands of ZeroThe Hacker News·Apr 8, 11:44 UTC · Apr 8, 2026Exploit / PoC60
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
AI models keep getting caught cheatingCyberScoop·Jul 21, 19:20 UTC · Jul 21, 2026Exploit / PoC in the wild60
Industry must take the lead in forming public-private cybersecurity partnerships, experts sayCyberScoop·Jun 30, 17:19 UTC · Jun 30, 2017Exploit / PoC in the wild60
Stop Your Legacy Infrastructure from Hijacking Your AI AgentsThe Hacker News·Jul 20, 06:32 UTC · Jul 20, 2026Exploit / PoC in the wildCVE-2025-2481360
AI Cyber Challenge Winners Revealed in DARPA’s $4M Cybersecurity ShowdInfosecurity Magazine·Aug 9, 11:45 UTC · Aug 9, 2025Exploit / PoC60
BigBear.ai to buy Ask Sage, strengthening securityCyberScoop·Nov 11, 15:02 UTC · Nov 11, 2025Exploit / PoC in the wild60
How Amazon Web Services uses AI to be a security ‘force multiplier’CyberScoop·Jun 11, 18:31 UTC · Jun 11, 2025Exploit / PoC in the wild60
Growing hacking threat to satellite systems compels global push to secure outer spaceCyberScoop·Jun 1, 21:26 UTC · Jun 1, 2023Exploit / PoC60
Microsoft debuts AI cybersecurity offerings as competition heats upCyberScoop·Jul 27, 23:47 UTC · Jul 27, 2026Exploit / PoC60
Reuters: OpenAI Agent Hacked Hugging Face for Days Before Being DetectedSecurity Affairs·Jul 27, 21:44 UTC · Jul 27, 2026Exploit / PoC60
Top 5 Attack Surface Risks of 2022Recorded Future·Aug 25, 00:00 UTC · Aug 25, 2025Exploit / PoC in the wildCVE-2022-30190CVE-2022-3786CVE-2022-360260
Anthropic's new model is Mythos on a leashCyberScoop·Jun 9, 19:46 UTC · Jun 9, 2026Exploit / PoC in the wild60
Closed briefing sets stage for House hearing on Anthropic’s Mythos and cyber risksCyberScoop·May 13, 23:13 UTC · May 13, 2026Exploit / PoC in the wild60
Tuskira’s Kairo exposes hidden AI-driven breach pathsHelp Net Security·May 13, 00:00 UTC · May 13, 2026Exploit / PoC60
Exaforce raises $125 million to respond to AI-powered attacksHelp Net Security·May 12, 00:00 UTC · May 12, 2026Exploit / PoC60
‘GrafanaGhost’ bypasses Grafana's AI defenses without leaving a traceCyberScoop·Apr 7, 17:01 UTC · Apr 7, 2026Exploit / PoC in the wild60
LLMs are getting better at unmasking people onlineCyberScoop·Mar 4, 20:56 UTC · Mar 4, 2026Exploit / PoC in the wild60
Anthropic Project Glasswing to Use AI to Fix Software Bugs With AIInfosecurity Magazine·Apr 8, 11:30 UTC · Apr 8, 2026Exploit / PoC60