Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Yajing Bai, Jinhao Duan, Jie Peng +4
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmar…
cs.CR2025
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
Yang Ouyang, Hengrui Gu, Shuhang Lin +6
As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical…