conftrace_

malicious actor

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

trust learning (1) vulnerabilities (1) tamper-resistant models (1) multi-agent system (1) large language model (1) social awareness (1) network topology (1) directed graph (1) knowledge editing (1)

Papers

Position: Editing Large Language Models Poses Serious Safety Risks ICML 2025 Learning Trust Over Directed Graphs in Multiagent Systems L4DC 2023