類似資料

• from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
  著者:: Yan, Yu, 等
  出版事項: (2025)
• Beyond Static Pattern Matching? Rethinking Automatic Cryptographic API Misuse Detection in the Era of LLMs
  著者:: Xia, Yifan, 等
  出版事項: (2024)
• SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
  著者:: Duan, Zenghao, 等
  出版事項: (2026)
• "MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale
  著者:: Yan, Biwei, 等
  出版事項: (2025)
• ConfusedPilot: Confused Deputy Risks in RAG-based LLMs
  著者:: RoyChowdhury, Ayush, 等
  出版事項: (2024)