Selection-Invariant Communication Compilers for Privacy-Aware Multi-Agent LLM Workflows
cs.AI, cs.CR
Submitted: 2026-08-04
Updated: 2026-08-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Securing AI Agents with Information-Flow Control
- Defeating Prompt Injections by Design
- AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
- Contextualized Privacy Defense for LLM Agents
- POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
- CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection