VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise

no code implementations • 5 Jun 2024 • Zhixun He, Mukesh Singhal

The empirical experiments show that the proposed VQUNet provides better robustness to the target DNN models, and it outperforms other state-of-the-art noise-reduction-based defense methods under various adversarial attacks for both Fashion-MNIST and CIFAR10 datasets.

Adversarial Attack Quantization +1