Topic
AI safety
-
News AI
Imperial and Fraunhofer study cuts LLM prompt injection attack success from 97% to 10%
European researchers developed Heads of Security, using learned per-head attention gates to enforce instruction-data separation in frontier language models.
-
News AI
Formatting shortcuts distort AI agent safety benchmarks by up to 11 points
A study auditing AI agent safety evaluations showed that superficial cues like tool names and prompt markers distort guardrail false-positive rates by up to 11.46 percentage points without altering underlying safety.