Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios

Documenti analoghi

• Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
  di: Yoon, Sangyeon, et al.
  Pubblicazione: (2026)
• Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
  di: Cebere, Tudor, et al.
  Pubblicazione: (2024)
• The Sample Complexity of Membership Inference and Privacy Auditing
  di: Haghifam, Mahdi, et al.
  Pubblicazione: (2025)
• Visual Privacy Auditing with Diffusion Models
  di: Schwethelm, Kristian, et al.
  Pubblicazione: (2024)
• Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
  di: Yoon, Sangyeon, et al.
  Pubblicazione: (2026)