A benchmark of 85 manually curated workplace scenarios reveals that multi-user AI agent systems suffer high rates of contextual integrity violations across outputs, inter-agent communication, and shared memory.
2506.17336 , archivePrefix=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2roles
method 1polarities
use method 1representative citing papers
BSGS-Diagonal plus fused GPU CKKS kernels cut rotation keys ~91% and speed encrypted face matching up to ~21× versus HyDia, with sub-second queries up to ~32K templates.
citing papers explorer
-
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
A benchmark of 85 manually curated workplace scenarios reveals that multi-user AI agent systems suffer high rates of contextual integrity violations across outputs, inter-agent communication, and shared memory.
-
Lightweight, Practical Encrypted Face Recognition with GPU Support
BSGS-Diagonal plus fused GPU CKKS kernels cut rotation keys ~91% and speed encrypted face matching up to ~21× versus HyDia, with sub-second queries up to ~32K templates.