Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation

Documenti analoghi

• Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor
  di: Chang, Wenhan, et al.
  Pubblicazione: (2026)
• Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
  di: Guan, Faqian, et al.
  Pubblicazione: (2024)
• Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs
  di: Xu, Heng, et al.
  Pubblicazione: (2024)
• Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications
  di: Xu, Heng, et al.
  Pubblicazione: (2024)
• Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
  di: Chang, Wenhan, et al.
  Pubblicazione: (2025)