Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning
cs.CR, cs.AI, cs.LG, cs.MA
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/jinxiy1104/FGLGuard
Terminology
Sources
- SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- $\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks
- Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
- Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
- FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
- Agent-SafetyBench: Evaluating the Safety of LLM Agents
- CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
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
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs