STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack

Documenti analoghi

• Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
  di: Yan, Yu, et al.
  Pubblicazione: (2026)
• DREAM: Dynamic Red-teaming across Environments for AI Models
  di: Lu, Liming, et al.
  Pubblicazione: (2025)
• Atoxia: Red-teaming Large Language Models with Target Toxic Answers
  di: Du, Yuhao, et al.
  Pubblicazione: (2024)
• MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
  di: Guo, Weiyang, et al.
  Pubblicazione: (2025)
• Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
  di: Chen, Xuan, et al.
  Pubblicazione: (2025)