ControlNET: A Firewall for RAG-based LLM System

Documenti analoghi

• BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
  di: Duan, Kaiwen, et al.
  Pubblicazione: (2025)
• FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
  di: Yao, Hongwei, et al.
  Pubblicazione: (2023)
• AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
  di: Ahmed, Chuadhry Mujeeb
  Pubblicazione: (2025)
• Confundo: Learning to Generate Robust Poison for Practical RAG Systems
  di: Hu, Haoyang, et al.
  Pubblicazione: (2026)
• MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification
  di: Luo, Xiang, et al.
  Pubblicazione: (2025)