Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representation
This addresses security-critical applications by enhancing robustness against adversarial attacks, though it appears incremental as it builds on existing denoising and frequency analysis methods.
The paper tackles the vulnerability of deep neural networks to adversarial attacks on images by proposing a two-phase training method that integrates spatial and frequency domain denoising using a transformer layer, resulting in substantially improved classification accuracy on datasets like MNIST, CIFAR-10, and Fashion-MNIST compared to existing denoising and adversarial training approaches.
In recent times, deep neural networks (DNNs) have been successfully adopted for various applications. Despite their notable achievements, it has become evident that DNNs are vulnerable to sophisticated adversarial attacks, restricting their applications in security-critical systems. In this paper, we present two-phase training methods to tackle the attack: first, training the denoising network, and second, the deep classifier model. We propose a novel denoising strategy that integrates both spatial and frequency domain approaches to defend against adversarial attacks on images. Our analysis reveals that high-frequency components of attacked images are more severely corrupted compared to their lower-frequency counterparts. To address this, we leverage Discrete Wavelet Transform (DWT) for frequency analysis and develop a denoising network that combines spatial image features with wavelets through a transformer layer. Next, we retrain the classifier using the denoised images, which enhances the classifier's robustness against adversarial attacks. Experimental results across the MNIST, CIFAR-10, and Fashion-MNIST datasets reveal that the proposed method remarkably elevates classification accuracy, substantially exceeding the performance by utilizing a denoising network and adversarial training approaches. The code is available at https://github.com/Mayank94/Trans-Defense.