Sep 2026· IEEE Transactions on Image Processing· Vol 35, pp. 9458-9471· 0 citations· 65 references
Medicine
Abstract
Deep Neural Networks (DNNs) remain vulnerable to adversarial perturbations, raising significant concerns in image processing applications, particularly in high-stakes domains such as medical imaging and security-critical systems. Most existing defense strategies are limited by domain specificity, architectural dependence, or the need for extensive retraining, making them impractical for real-world deployment. In this work, we propose ADEx, the first framework to integrate low-rank image approximation with explainability-driven analysis for the detection of adversarial samples. ADEx works by extracting a low-rank representation of the input image using Singular Value Thresholding (SVT), and identifying important image regions by computing class-specific gradient maps from the final layers of the classifier. These maps are then compared using Rank-Biased Overlap (RBO) to quantify the degree of attention drift induced by adversarial perturbations. ADEx is designed for adversarial detection in image classification systems, where class-specific gradient-based explanations are well defined. The framework operates without retraining or architectural modification and can be applied to a wide range of differentiable classifiers, provided gradient access is available for explanation generation. Extensive experiments across multiple datasets, architectures, and attack types demonstrate consistent performance, robustness to hyperparameter choices, and low sensitivity to calibration size. The method provides an interpretable and lightweight solution suitable for practical deployment.
This work suggests that existing AI-generated image detectors are easily deceived by adversarial perturbations, highlighting the need for more robust detectors.
Yun-Yun Tsai, Rui Xu, Chengzhi Mao et al.· 0 citations
The integration of deep learning models into image preprocessing pipelines such as super-resolution introduces a largely unexplored attack vector for adversaries targeting downstream tasks. To ensure trustworthiness of critical imaging pipelines, we must be able to detect adversarial behavior within preprocessing model...
Emma J. Reid, Haley Duba-Sullivan, Tony G. Allen· arXiv.org· 0 citations
This work proposes two novel attack methods targeted at detectors that leverage autoencoder reconstruction error and finds that by constructing imperceptible adversarial examples, the distance between original and reconstruction can be artificially increased, causing fake images to be wrongly classified as real.
R. Demchenko, Jonas Ricker, Asja Fischer· 0 citations
This study seeks to discern whether images featuring avatars can be effectively used to generate adversarial examples capable of fully masking a person, and establishes a method of utilizing virtual avatars to provide increased privacy for users.
AdROD outperforms five baseline defenses and exhibits superior generalizability compared with the evaluated adversarial-training baselines, while maintaining real-time performance for safely stopping the vehicle at a stop sign instrumented with adversarial patches.
Yuting Wu, Dongfang Guo, Xiangzhong Luo et al.· 0 citations
Density-Weighted Adversarial Training is presented, a plug-in framework that spreads training over a set of sampled ϵ-balls and reweights each candidate adversarial example by a Gaussian density of its distance from the benign sample, and it is proved that the population objective upper-bounds the worst-case adversaria...