mlsanityData to 14 Oct 2026

Adversarial Detection with a Dynamically Stable System

arXiv 2411.06666 ↗First posted 11 Nov 2024cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial detection is designed to identify and reject maliciously crafted adversarial examples(AEs) which are generated to disrupt the classification of target models. Presently, various input transformation-based methods have been developed on adversarial example detection, which typically rely on empirical experience and lead to unreliability against new attacks. To address this issue, we propose and conduct a Dynamically Stable System (DSS), which can effectively detect the adversarial examples from normal examples according to the stability of input examples. Particularly, in our paper, the generation of adversarial examples is considered as the perturbation process of a Lyapunov dynamic system, and we propose an example stability mechanism, in which a novel control term is added in adversarial example generation to ensure that the normal examples can achieve dynamic stability while the adversarial examples cannot achieve the stability. Then, based on the proposed example stability mechanism, a Dynamically Stable System (DSS) is proposed, which can utilize the disruption and restoration actions to determine the stability of input examples and detect the adversarial examples through changes in the stability of the input examples. In comparison with existing methods in three benchmark datasets(MNIST, CIFAR10, and CIFAR100), our evaluation results show that our proposed DSS can achieve ROC-AUC values of 99.83%, 97.81% and 94.47%, surpassing the state-of-the-art(SOTA) values of 97.35%, 91.10% and 93.49% in the other 7 methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

29 of 38 references.

References · 29

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  8. 2018Robustness May Be at Odds with Accuracycited by 880
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  10. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  12. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
17 more
  1. 2017Detecting Adversarial Samples from Artifactscited by 245
  2. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 207
  3. 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
  4. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  5. 2019Functional Adversarial Attackscited by 82
  6. 2018Adversarial vulnerability for any classifiercited by 78
  7. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  8. 2021Subspace Adversarial Trainingcited by 41
  9. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  10. 2020Randomization matters. How to defend against strong adversarial attackscited by 37
  11. 2018Partial Convolution based Paddingcited by 29
  12. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  13. 2020A General Framework For Detecting Anomalous Inputs to DNN Classifierscited by 24
  14. 2023Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Scorecited by 20
  15. 2019Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Searchcited by 19
  16. 2021Out of Distribution Detection and Adversarial Attacks on Deep Neural Networks for Robust Medical Image Analysiscited by 10
  17. 2020Adversarial Examples Detection and Analysis with Layer-wise Autoencoderscited by 9

Built on by

Not cited yet.