類似資料

• ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
  著者:: Wang, Che, 等
  出版事項: (2026)
• Can Indirect Prompt Injection Attacks Be Detected and Removed?
  著者:: Chen, Yulin, 等
  出版事項: (2025)
• TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
  著者:: Chen, Yulin, 等
  出版事項: (2025)
• Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
  著者:: Zhong, Yinan, 等
  出版事項: (2025)
• ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
  著者:: Zhao, Wei, 等
  出版事項: (2026)