ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

Documenti analoghi

• GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio
  di: Zhu, Zhenhao, et al.
  Pubblicazione: (2026)
• Prompt Inversion Attack against Collaborative Inference of Large Language Models
  di: Qu, Wenjie, et al.
  Pubblicazione: (2025)
• FlipAttack: Jailbreak LLMs via Flipping
  di: Liu, Yue, et al.
  Pubblicazione: (2024)
• Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
  di: Wang, Yuhao, et al.
  Pubblicazione: (2025)
• $\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models
  di: Weng, Fenghua, et al.
  Pubblicazione: (2024)