Lignende værker

• SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
  af: Formento, Brian, et al.
  Udgivet: (2024)
• Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
  af: Liu, Renyang, et al.
  Udgivet: (2025)
• User Inference Attacks on Large Language Models
  af: Kandpal, Nikhil, et al.
  Udgivet: (2023)
• Composite Backdoor Attacks Against Large Language Models
  af: Huang, Hai, et al.
  Udgivet: (2023)
• TFL: Targeted Bit-Flip Attack on Large Language Model
  af: Guo, Jingkai, et al.
  Udgivet: (2026)