Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representation
- URL: http://arxiv.org/abs/2510.27245v1
- Date: Fri, 31 Oct 2025 07:29:50 GMT
- Title: Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representation
- Authors: Alik Pramanick, Mayank Bansal, Utkarsh Srivastava, Suklav Ghosh, Arijit Sur,
- Abstract summary: Deep neural networks (DNNs) are vulnerable to adversarial attacks, restricting their applications in security-critical systems.<n>We present two-phase training methods to tackle the attack: first, training the denoising network, and second, the deep classifier model.<n>We propose a novel denoising strategy that integrates both spatial and frequency domain approaches to defend against adversarial attacks on images.
- Score: 11.290034765506816
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection [9.516391314161154]
We study the adversarial robustness of AI-generated image detectors, focusing on Contrastive Language-Image Pretraining (CLIP)-based methods.
CLIP-based detectors are found to be vulnerable to white-box attacks just like CNN-based detectors.
This analysis provides new insights into the properties of forensic detectors that can help to develop more effective strategies.
arXiv Detail & Related papers (2024-07-28T18:20:08Z) - VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise [0.5755004576310334]
We introduce a novel noise-reduction procedure, Vector Quantization U-Net (VQUNet), to reduce adversarial noise and reconstruct data with high fidelity.
VQUNet features a discrete latent representation learning through a multi-scale hierarchical structure for both noise reduction and data reconstruction.
It outperforms other state-of-the-art noise-reduction-based defense methods under various adversarial attacks for both Fashion-MNIST and CIFAR10 datasets.
arXiv Detail & Related papers (2024-06-05T10:10:03Z) - Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detection [4.8687338715585415]
Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning.<n>SNNs are vulnerable to adversarial attacks like convolutional neural networks.<n>We propose a biologically inspired methodology to enhance the robustness of SNNs.
arXiv Detail & Related papers (2024-04-26T00:57:06Z) - Distributed Adversarial Training to Robustify Deep Neural Networks at
Scale [100.19539096465101]
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification.
To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training.
We propose a large-batch adversarial training framework implemented over multiple machines.
arXiv Detail & Related papers (2022-06-13T15:39:43Z) - Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation [94.30136898739448]
We show the existence of a textbftraining-free adversarial perturbation under the no-box threat model.<n>Motivated by our observation that high-frequency component (HFC) domains in low-level features, we attack an image mainly by manipulating its frequency components.<n>Our method is even competitive to mainstream transfer-based black-box attacks.
arXiv Detail & Related papers (2022-03-09T09:51:00Z) - Combating Adversaries with Anti-Adversaries [118.70141983415445]
In particular, our layer generates an input perturbation in the opposite direction of the adversarial one.
We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models.
Our anti-adversary layer significantly enhances model robustness while coming at no cost on clean accuracy.
arXiv Detail & Related papers (2021-03-26T09:36:59Z) - WaveTransform: Crafting Adversarial Examples via Input Decomposition [69.01794414018603]
We introduce WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination)
Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs.
arXiv Detail & Related papers (2020-10-29T17:16:59Z) - Online Alternate Generator against Adversarial Attacks [144.45529828523408]
Deep learning models are notoriously sensitive to adversarial examples which are synthesized by adding quasi-perceptible noises on real images.
We propose a portable defense method, online alternate generator, which does not need to access or modify the parameters of the target networks.
The proposed method works by online synthesizing another image from scratch for an input image, instead of removing or destroying adversarial noises.
arXiv Detail & Related papers (2020-09-17T07:11:16Z) - Defending Adversarial Examples via DNN Bottleneck Reinforcement [20.08619981108837]
This paper presents a reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
By reinforcing the former while maintaining the latter, any redundant information, be it adversarial or not, should be removed from the latent representation.
In order to reinforce the information bottleneck, we introduce the multi-scale low-pass objective and multi-scale high-frequency communication for better frequency steering in the network.
arXiv Detail & Related papers (2020-08-12T11:02:01Z) - Towards Achieving Adversarial Robustness by Enforcing Feature
Consistency Across Bit Planes [51.31334977346847]
We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction.
We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
arXiv Detail & Related papers (2020-04-01T09:31:10Z) - TensorShield: Tensor-based Defense Against Adversarial Attacks on Images [7.080154188969453]
Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks.
In this paper, we utilize tensor decomposition techniques as a preprocessing step to find a low-rank approximation of images which can significantly discard high-frequency perturbations.
arXiv Detail & Related papers (2020-02-18T00:39:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.