TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks

Documenti analoghi

• Exploring the Robustness and Transferability of Patch-Based Adversarial Attacks in Quantized Neural Networks
  di: Guesmi, Amira, et al.
  Pubblicazione: (2024)
• ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches
  di: Chattopadhyay, Nandish, et al.
  Pubblicazione: (2023)
• Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks
  di: Chattopadhyay, Nandish, et al.
  Pubblicazione: (2024)
• Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs
  di: Guesmi, Amira, et al.
  Pubblicazione: (2025)
• TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization
  di: Guesmi, Amira, et al.
  Pubblicazione: (2025)