TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Documenti analoghi

• PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
  di: Zou, Wei, et al.
  Pubblicazione: (2024)
• SecInfer: Preventing Prompt Injection via Inference-time Scaling
  di: Liu, Yupei, et al.
  Pubblicazione: (2025)
• Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
  di: Wu, Yu-Hang, et al.
  Pubblicazione: (2025)
• Evaluating LLM-based Personal Information Extraction and Countermeasures
  di: Liu, Yupei, et al.
  Pubblicazione: (2024)
• Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution
  di: Rattanavipanon, Norrathep, et al.
  Pubblicazione: (2024)