AI Security Institute Advocates Security Best Practices After Mythos TInfosecurity Magazine·Apr 14, 09:30 UTC · Apr 14, 2026Exploit / PoC60
Top AI companies have spent months working with US, UK governments on model safetyCyberScoop·Sep 15, 20:37 UTC · Sep 15, 2025Exploit / PoC in the wild60
Testing reveals Claude Mythos's offensive capabilities and limitsHelp Net Security·Aug 5, 12:04 UTC · Aug 5, 2026Exploit / PoC60
OpenAI Pauses Astra Model Over Critical Cybersecurity Risk ConcernsSecurity Affairs·Aug 10, 11:16 UTC · Aug 10, 2026Exploit / PoC160
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
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
Here’s how cyber heavyweights in the US and UK are dealing with Claude MythosCyberScoop·Apr 13, 21:43 UTC · Apr 13, 2026Exploit / PoC in the wild60
Researchers say AI just broke every benchmark for autonomous cyber capabilityCyberScoop·May 13, 22:29 UTC · May 13, 2026Exploit / PoC in the wild60
AI Cyber Challenge Winners Revealed in DARPA’s $4M Cybersecurity ShowdInfosecurity Magazine·Aug 9, 11:45 UTC · Aug 9, 2025Exploit / PoC60
AI models keep getting caught cheatingCyberScoop·Jul 21, 19:20 UTC · Jul 21, 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
Week in review: Axios npm supply chain compromise, critical FortiClient EMS bugs exploitedHelp Net Security·Apr 5, 00:00 UTC · Apr 5, 2026Exploit / PoC in the wildCVE-2026-35616CVE-2026-21643CVE-2026-20093+2 CVEs160
OpenAI AI models exploited zero-days to reach Hugging Face in benchmark testSecurity Affairs·Jul 22, 08:52 UTC · Jul 22, 2026Exploit / PoC60
AI Companies To Play Bigger Role in CVE Program, Says CISAInfosecurity Magazine·Apr 15, 10:30 UTC · Apr 15, 2026Exploit / PoC60
Report: Anthropic Deploys Engineers to Support NSA Use of MythosSecurity Affairs·Jun 6, 16:18 UTC · Jun 6, 2026Exploit / 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
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
A case for how to shape ‘ingredient lists’ for AI modelsCyberScoop·Jun 16, 16:00 UTC · Jun 16, 2026Exploit / 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
Policymakers grapple with fallout from Chinese AICyberScoop·Dec 18, 23:08 UTC · Dec 18, 2025Exploit / PoC60
Treasury report calls out cyber risks to financial sector fueled by AICyberScoop·Mar 29, 18:20 UTC · Mar 29, 2024Exploit / PoC in the wild60
AI chatbots want your geolocation data. Privacy experts say beware.CyberScoop·Jun 8, 20:46 UTC · Jun 8, 2023Exploit / PoC in the wild60
UN seeks to build consensus on ‘safe, secure and trustworthy’ AICyberScoop·Sep 26, 20:31 UTC · Sep 26, 2025Exploit / PoC in the wild60
Open access to AI foundational models poses various security and compliance risks, report findsCyberScoop·Dec 13, 11:00 UTC · Dec 13, 2023Exploit / PoC in the wild60
Week in review: Atlassian Confluence RCE PoC, new Kali Linux, Patch Tuesday forecastHelp Net Security·Jun 9, 00:00 UTC · Jun 9, 2024Exploit / PoCCVE-2024-21683CVE-2024-28995CVE-2024-29972+4 CVEs60
Anthropic expanding access to Project GlasswingCyberScoop·Jun 3, 13:24 UTC · Jun 3, 2026Exploit / PoC in the wild60
Coming to DEF CON 31: Hacking AI modelsCyberScoop·May 4, 18:16 UTC · May 4, 2023Exploit / PoC in the wild60
Week in review: Google fixes yet another Chrome zero-day exploit, YouTube as a cybercrime channelHelp Net Security·May 26, 00:00 UTC · May 26, 2024Exploit / PoC in the wildCVE-2024-5274CVE-2024-4985CVE-2023-43208+4 CVEs60
Soltra to be shut down by financial sector partnersCyberScoop·Nov 18, 15:44 UTC · Nov 18, 2016Exploit / PoC in the wild60
Treasury official: Small financial institutions have ‘growth to do’ in using AI against threatsCyberScoop·Apr 19, 15:45 UTC · Apr 19, 2024Exploit / PoC in the wild60
Major world economies spell out key elements of AI ‘ingredients list’CyberScoop·May 12, 21:09 UTC · May 12, 2026Exploit / PoC in the wild60
Growing reliance on satellites requires new approach to cybersecurity in space, expert saysCyberScoop·Jul 11, 19:35 UTC · Jul 11, 2023Exploit / PoC in the wild60
White House details ‘Gold Eagle’ clearinghouse for AI cyber threatsCyberScoop·Jul 14, 23:22 UTC · Jul 14, 2026Exploit / PoC in the wild60
Open letter calls for prohibition on superintelligent AI, highlighting growing mainstream concernCyberScoop·Oct 22, 16:22 UTC · Oct 22, 2025Exploit / PoC in the wild60
Week in review: Google fixes exploited Chrome zero-day, Patch Tuesday forecastHelp Net Security·Jun 8, 00:00 UTC · Jun 8, 2025Exploit / PoC in the wildCVE-2025-541960
Conifers rolls out AI-powered SOC for unified security operations and automated responseHelp Net Security·May 26, 00:00 UTC · May 26, 2026Exploit / PoC in the wild60
Task force unveils cyber recommendations for the next presidentCyberScoop·Oct 22, 21:24 UTC · Oct 22, 2024Exploit / PoC in the wild60
North Korea hasn't stopped launching cyberattacks amid peace talksCyberScoop·May 30, 21:17 UTC · May 30, 2018Exploit / PoC in the wild60
Week in review: Covertly connected and insecure Android VPN apps, Apple fixes exploited zero-dayHelp Net Security·Aug 24, 00:00 UTC · Aug 24, 2025Exploit / PoC in the wildCVE-2025-43300CVE-2018-0171CVE-2025-31324+1 CVEs60
Anthropic and OpenAI Security Tools Could Fuel CyberInfosecurity Magazine·Jul 10, 13:45 UTC · Jul 10, 2026Exploit / PoC60