Malicious ML models found on Hugging Face HubHelp Net Security·Feb 10, 00:00 UTC · Feb 10, 2025Exploit / PoC145
Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade DetectionThe Hacker News·Feb 10, 04:09 UTC · Feb 10, 2025Exploit / PoC57
Malicious AI Models on Hugging Face Exploit Novel Attack TechniqueInfosecurity Magazine·Feb 7, 14:00 UTC · Feb 7, 2025Exploit / PoC45
Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running ItThe Hacker News·Jul 9, 05:17 UTC · Jul 9, 2026Exploit / PoCCVE-2026-3986150
NVIDIA Triton Bugs Let Unauthenticated Attackers Execute Code and Hijack AI ServersThe Hacker News·Aug 6, 09:08 UTC · Aug 6, 2025Exploit / PoC in the wildCVE-2025-23319CVE-2025-23320CVE-2025-23334+3 CVEs60
Hugging Face platform continues to be plagued by vulnerable ‘pickles’CyberScoop·Feb 6, 16:34 UTC · Feb 6, 2025Exploit / PoC in the wild60
Washington summit grapples with securing open source softwareCyberScoop·Sep 13, 13:30 UTC · Sep 13, 2023Exploit / PoC in the wild60
HPE's new solution standardizes machine learning workflows and accelerates AI deploymentsHelp Net Security·Jan 22, 08:53 UTC · Jan 22, 2020Exploit / PoC45