When Alignment Isn't Enough: Response-Path Attacks on LLM Agents

Documenti analoghi

• CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
  di: Liu, Zesen, et al.
  Pubblicazione: (2025)
• When Trust Isn't Enough.
  di: Behrman, Sara
  Pubblicazione: (1998)
• From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
  di: Zhang, Zhixiang, et al.
  Pubblicazione: (2026)
• Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
  di: Wang, Chaoyang, et al.
  Pubblicazione: (2025)
• When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions
  di: Cao, Zhuo, et al.
  Pubblicazione: (2025)