Safety 5
- [PaRev] INFA-Guard: Infection-Aware MAS Safeguarding
- [PaRev] On the Role of Attention Heads in Large Language Models Safety
- [PaRev] Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
- [PaRev] G-Safeguard: A Topology-Guided Security Lens for LLM-based Multi-Agent Systems
- [PaRev] Programming Refusal with Conditional Activation Steering (CAST)