cs.CVOct 3, 2025

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

Organizations: LSU Vision Lab · UCLA Vision Lab · Yale Vision Lab

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.

Figures & tables

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation

    Jun 21, 2026Adam Koziak, Yuhong GuoTest-Time AdaptationEnsemble Learning

  2. DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing

    Jan 18, 2026Jinwei Hu, Shiyuan Meng, Yi Dong +1Adversarial AttacksAdversarial Robustness

  3. Learning Robustness at Test-Time from a Non-Robust Teacher

    Apr 13, 2026Stefano Bianchettin, Giulio Rossolini, Giorgio ButtazzoAdversarial RobustnessTest-Time Adaptation