Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment

Documenti analoghi

• Can Current Detectors Catch Face-to-Voice Deepfake Attacks?
  di: Nguyen, Nguyen Linh Bao, et al.
  Pubblicazione: (2025)
• BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
  di: Vo, Viet Quoc, et al.
  Pubblicazione: (2024)
• NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
  di: Nguyen, David D., et al.
  Pubblicazione: (2026)
• Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
  di: Wang, Nan, et al.
  Pubblicazione: (2025)
• Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
  di: Ma, Hua, et al.
  Pubblicazione: (2025)