External Data Extraction Attacks against Retrieval-Augmented Large Language Models

Documenti analoghi

• ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
  di: Yang, Yuchen, et al.
  Pubblicazione: (2024)
• Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
  di: He, Yu, et al.
  Pubblicazione: (2025)
• SoK: Large Language Model Copyright Auditing via Fingerprinting
  di: Shao, Shuo, et al.
  Pubblicazione: (2025)
• DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
  di: Shao, Shuo, et al.
  Pubblicazione: (2025)
• Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
  di: Chen, Yukun, et al.
  Pubblicazione: (2025)