Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models

Documenti analoghi

• Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
  di: He, Yuhao, et al.
  Pubblicazione: (2024)
• Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance
  di: Eser, Çağrı, et al.
  Pubblicazione: (2025)
• Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
  di: Bellchambers, Gregory
  Pubblicazione: (2025)
• ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages
  di: Hull, Matthew, et al.
  Pubblicazione: (2025)
• DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
  di: Li, Fengpeng, et al.
  Pubblicazione: (2024)