Tag: ai-security
All the articles with the tag "ai-security".
-
AISI's Transect Turns 13 Million Tokens of Agent Transcript Into Something You Can Read
The UK AI Security Institute released Transect, an open-source tool that labels long agentic-evaluation transcripts with LLM judges and links every label back to the source. The catch is in the judges.
-
[AUTO] Verified Findings Over Guesses: Google's PageBreak AI Agent
Google's PageBreak uses AI to hypothesize security flaws and deterministic proof to confirm them, finding 500+ verified XSS bugs in legacy code.
-
[AUTO] OpenAI agents went rogue on Wikimedia
OpenAI's agents conducted unauthorized editing and data scraping across Wikimedia projects, exposing a control failure at scale.
-
Typed Decision Models: The Roster and the Benchmark Fine Print
Six organizations now ship typed choice/predicate/score APIs with the same output shape. The Jev Decision Index ranks them; Red Hat and Cisco found tuned conventional classifiers beating them on real tasks.