mlsanityData to 7 Oct 2026

Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networks

arXiv 2105.10101 ↗First posted 21 May 2021cs.LG eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have been shown vulnerable to Test-Time Evasion attacks (TTEs, or adversarial examples), which, by making small changes to the input, alter the DNN's decision. We propose an unsupervised attack detector on DNN classifiers based on class-conditional Generative Adversarial Networks (GANs). We model the distribution of clean data conditioned on the predicted class label by an Auxiliary Classifier GAN (AC-GAN). Given a test sample and its predicted class, three detection statistics are calculated based on the AC-GAN Generator and Discriminator. Experiments on image classification datasets under various TTE attacks show that our method outperforms previous detection methods. We also investigate the effectiveness of anomaly detection using different DNN layers (input features or internal-layer features) and demonstrate, as one might expect, that anomalies are harder to detect using features closer to the DNN's output layer.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 74 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

44 of 74 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
32 more
  1. 2019When Does Label Smoothing Help?cited by 985
  2. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  3. 2018Robustness May Be at Odds with Accuracycited by 873
  4. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  11. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  12. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  13. 2018cGANs with Projection Discriminatorcited by 253
  14. 2017Detecting Adversarial Samples from Artifactscited by 244
  15. 2017On Detecting Adversarial Perturbationscited by 232
  16. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  17. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  18. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  19. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  20. 2018Efficient GAN-Based Anomaly Detectioncited by 122
  21. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  22. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  23. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  24. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  25. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  26. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  27. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  28. 2020Targeted Attack for Deep Hashing based Retrievalcited by 34
  29. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  30. 2019GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classificationcited by 20
  31. 2021Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Votingcited by 16
  32. 2017When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Timecited by 9

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizationscited by 5
  2. 2023MTS-DVGAN: Anomaly Detection in Cyber-Physical Systems using a Dual Variational Generative Adversarial Networkcited by 5
  3. 2025A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systemscited by 0