Tag: ai-security
All the articles with the tag "ai-security".
-
[AUTO] Data Diodes as AI Training Boundaries
Intuition Machines proposes hardware boundaries to contain frontier AI training, but adoption gaps raise questions about real risk and competitive incentives.
-
[AUTO] AI agents executed ransomware in hours
Frontier AI models deployed in a ransomware attack completed a network breach in 10 hours, adapting in real time without zero-days or elite tradecraft.
-
[AUTO] Malicious git configs execute code before approval
AI coding agents run code from .git/config during startup before showing trust prompts.
-
[AUTO] Claude Assists in PLC Exploit Porting, Not Automating It
Forescout researchers used Claude to port an RCE exploit between WAGO PLCs, but it required 8+ hours of guidance and API costs to work.