Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization

Documenti analoghi

• Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
  di: Sahabandu, Dinuka, et al.
  Pubblicazione: (2024)
• CANTXSec: A Deterministic Intrusion Detection and Prevention System for CAN Bus Monitoring ECU Activations
  di: Donadel, Denis, et al.
  Pubblicazione: (2025)
• CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
  di: Li, Yuetai, et al.
  Pubblicazione: (2024)
• BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  di: Xiang, Zhen, et al.
  Pubblicazione: (2024)
• OSLO: One-Shot Label-Only Membership Inference Attacks
  di: Peng, Yuefeng, et al.
  Pubblicazione: (2024)