MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication
Jinghan Xu, Longze Fan, Zeyuan Wang, Xinjin Li, Hankai Liu
cs.CR, cs.AI
Submitted: 2026-08-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems
- Securing AI Agents with Information-Flow Control
- Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems
- AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
- ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
- MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation
- Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Unveiling Privacy Risks in LLM Agent Memory
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
- Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
- AgentDAM: Privacy Leakage Evaluation for Autonomous Web 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
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills