Certified but Fooled! Breaking Certified Defences with Ghost Certificates

Documenti analoghi

• BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
  di: Vo, Viet Quoc, et al.
  Pubblicazione: (2024)
• Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
  di: Deng, Jieren, et al.
  Pubblicazione: (2024)
• Bayesian Learned Models Can Detect Adversarial Malware For Free
  di: Doan, Bao Gia, et al.
  Pubblicazione: (2024)
• Certifiably Robust Image Watermark
  di: Jiang, Zhengyuan, et al.
  Pubblicazione: (2024)
• StyleFool: Fooling Video Classification Systems via Style Transfer
  di: Cao, Yuxin, et al.
  Pubblicazione: (2022)