Confundo: Learning to Generate Robust Poison for Practical RAG Systems

Documenti analoghi

• Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning
  di: Zhang, Rui, et al.
  Pubblicazione: (2024)
• On the Adversarial Robustness of Graph Neural Networks with Graph Reduction
  di: Wu, Kerui, et al.
  Pubblicazione: (2024)
• RADAR: Defending RAG Dynamically against Retrieval Corruption
  di: Chen, Ziyuan, et al.
  Pubblicazione: (2026)
• Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
  di: Chow, Ka-Ho, et al.
  Pubblicazione: (2024)
• On the Efficiency of Privacy Attacks in Federated Learning
  di: Tabassum, Nawrin, et al.
  Pubblicazione: (2024)