Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment

Documenti analoghi

• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection
  di: Zheng, Jingnan, et al.
  Pubblicazione: (2026)
• Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
  di: Cui, Chenhang, et al.
  Pubblicazione: (2026)
• Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
  di: Cui, Chenhang, et al.
  Pubblicazione: (2024)
• RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
  di: Zheng, Jingnan, et al.
  Pubblicazione: (2025)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
  di: Cui, Chenhang, et al.
  Pubblicazione: (2024)