Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre

Documenti analoghi

• AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
  di: Carlini, Nicholas, et al.
  Pubblicazione: (2025)
• Robustness bounds on the successful adversarial examples in probabilistic models: Implications from Gaussian processes
  di: Maeshima, Hiroaki, et al.
  Pubblicazione: (2024)
• Remote Timing Attacks on Efficient Language Model Inference
  di: Carlini, Nicholas, et al.
  Pubblicazione: (2024)
• Evading Black-box Classifiers Without Breaking Eggs
  di: Debenedetti, Edoardo, et al.
  Pubblicazione: (2023)
• Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
  di: Tramèr, Florian, et al.
  Pubblicazione: (2022)