Task-graph contextual integrity limits multi-agent privacy leaks
On MAPLE-Bench's 144 cases, TG-CI cut mean unauthorized disclosures 85.8-94.1% while keeping 93.6-96.1% of baseline task accuracy.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #contextual-integrity
LLMs and Contextual Integrity
Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.
4