Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation
cs.CR, cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injection
- Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation
- Large Language Model Agent: A Survey on Methodology, Applications and Challenges
- IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
- WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
- Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
- G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data