Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

• URL: http://arxiv.org/abs/2510.03224v1
• Date: Fri, 03 Oct 2025 17:57:25 GMT
• Title: Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
• Authors: Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie, Yangchao Wu, Alex Wong, Stefano Soatto,
• Abstract summary: We propose a test-time defense mechanism against adversarial attacks.<n> imperceptible image perturbations that significantly alter the predictions of a model.<n>We show that our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.
• Score: 42.57676672281981
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.

Related papers

• Active Adversarial Noise Suppression for Image Forgery Localization [56.98050814363447]
  We introduce an Adversarial Noise Suppression Module (ANSM) that generate a defensive perturbation to suppress the attack effect of adversarial noise.<n>To our best knowledge, this is the first report of adversarial defense in image forgery localization tasks.
  arXiv  Detail & Related papers  (2025-06-15T14:53:27Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Anomaly Unveiled: Securing Image Classification against Adversarial Patch Attacks [3.6275442368775512]
  Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. In this paper, we investigate the behavior of adversarial patches as anomalies within the distribution of image information. Our proposed defense mechanism utilizes a clustering-based technique called DBSCAN to isolate anomalous image segments.
  arXiv  Detail & Related papers  (2024-02-09T08:52:47Z)
• Adversarial Purification of Information Masking [8.253834429336656]
  Adrial attacks generate minuscule, imperceptible perturbations to images to deceive neural networks. Counteracting these, adversarial purification methods seek to transform adversarial input samples into clean output images to defend against adversarial attacks. We propose a novel adversarial purification approach named Information Mask Purification (IMPure) to extensively eliminate adversarial perturbations.
  arXiv  Detail & Related papers  (2023-11-26T15:50:19Z)
• IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks [16.577595936609665]
  We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. We show that our method significantly enhances the adversarial robustness of diverse deep models against various attacks while maintaining high accuracy on clean images.
  arXiv  Detail & Related papers  (2023-10-18T11:19:32Z)
• Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting [133.55037976429088]
  We investigate the adversarial robustness of vision transformers equipped with BERT pretraining (e.g., BEiT, MAE) A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. We propose a simple yet effective way to boost the adversarial robustness of MAE.
  arXiv  Detail & Related papers  (2023-08-20T16:27:17Z)
• Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness [1.2289361708127877]
  CARSO is able to defend itself against adaptive end-to-end white-box attacks devised for defences.<n>Our method improves by a significant margin the state-of-the-art for Cifar-10, Cifar-100, and TinyImageNet-200.
  arXiv  Detail & Related papers  (2023-05-25T09:04:31Z)
• Meta Adversarial Perturbations [66.43754467275967]
  We show the existence of a meta adversarial perturbation (MAP) MAP causes natural images to be misclassified with high probability after being updated through only a one-step gradient ascent update. We show that these perturbations are not only image-agnostic, but also model-agnostic, as a single perturbation generalizes well across unseen data points and different neural network architectures.
  arXiv  Detail & Related papers  (2021-11-19T16:01:45Z)
• Detecting Patch Adversarial Attacks with Image Residuals [9.169947558498535]
  A discriminator is trained to distinguish between clean and adversarial samples. We show that the obtained residuals act as a digital fingerprint for adversarial attacks. Results show that the proposed detection method generalizes to previously unseen, stronger attacks.
  arXiv  Detail & Related papers  (2020-02-28T01:28:22Z)
• Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition [56.844587127848854]
  We demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. We employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.
  arXiv  Detail & Related papers  (2020-02-22T10:08:42Z)

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.