contextual-integrity

Tag

Cards List
#contextual-integrity

Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?

Hugging Face Daily Papers · 2026-06-22 Cached

This paper introduces AgentCIBench, a benchmark to evaluate privacy risks in computer-use agents, finding that 11 of 15 frontier agents leak information in over 50% of scenarios.

0 favorites 0 likes
#contextual-integrity

RedactionBench

arXiv cs.CL · 2026-06-18 Cached

RedactionBench is a manually annotated benchmark for evaluating contextual PII redaction in large language models, introducing the R-Score metric and showing that contextual redaction remains an unsolved problem.

0 favorites 0 likes
#contextual-integrity

Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

arXiv cs.AI · 2026-06-15 Cached

This paper introduces Minim, a trusted local broker that performs privacy-aware minimization of UI observations for LLM-powered agents, using contextual integrity to balance task necessity and sensitivity scores. Experiments on WebArena show it reduces irrelevant sensitive leakage while preserving task-critical information.

0 favorites 0 likes
#contextual-integrity

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

arXiv cs.LG · 2026-05-21 Cached

Proposes Complementary Self-Distillation (SelfCI) to improve contextual integrity in LLMs by balancing utility and privacy. Evaluated on CI-RL and PrivacyLens benchmarks across multiple models.

0 favorites 0 likes
← Back to home

Submit Feedback