mlsanityData to 7 Oct 2026

APE-GAN: Adversarial Perturbation Elimination with GAN

arXiv 1707.05474 ↗First posted 18 Jul 2017cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Although neural networks could achieve state-of-the-art performance while recongnizing images, they often suffer a tremendous defeat from adversarial examples--inputs generated by utilizing imperceptible but intentional perturbation to clean samples from the datasets. How to defense against adversarial examples is an important problem which is well worth researching. So far, very few methods have provided a significant defense to adversarial examples. In this paper, a novel idea is proposed and an effective framework based Generative Adversarial Nets named APE-GAN is implemented to defense against the adversarial examples. The experimental results on three benchmark datasets including MNIST, CIFAR10 and ImageNet indicate that APE-GAN is effective to resist adversarial examples generated from five attacks.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 8; 2023: 11; 2024: 12; 2025: 7; 2026: 1.

57 papers.

Sort:

By area:

  1. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  2. 2021Ensembling with Deep Generative Viewscited by 53
  3. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
  4. 2023Towards quantum enhanced adversarial robustness in machine learningcited by 26
  5. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  6. 2022Restricted Black-box Adversarial Attack Against DeepFake Face Swappingcited by 25
  7. 2021Unrestricted Adversarial Attacks on ImageNet Competitioncited by 23
  8. 2021Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamicscited by 19
  9. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18
  10. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  11. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  12. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
38 more
  1. 2021Local Competition and Stochasticity for Adversarial Robustness in Deep Learningcited by 12
  2. 2022Analysis and Extensions of Adversarial Training for Video Classificationcited by 11
  3. 2021Modeling Adversarial Noise for Adversarial Trainingcited by 8
  4. 2022Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networkscited by 6
  5. 2022Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generatorcited by 5
  6. 2023Adversarial Sampling for Fairness Testing in Deep Neural Networkcited by 5
  7. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  8. 2024Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attackscited by 5
  9. 2022General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignmentscited by 4
  10. 2024Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantizationcited by 4
  11. 2021Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Trainingcited by 3
  12. 2024Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replaycited by 3
  13. 2021On the role of feedback in visual processing: a predictive coding perspectivecited by 2
  14. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  15. 2024VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noisecited by 2
  16. 2025Robustness Feature Adapter for Efficient Adversarial Trainingcited by 2
  17. 2021CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purificationcited by 1
  18. 2021Improving Global Adversarial Robustness Generalization With Adversarially Trained GANcited by 1
  19. 2022Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustnesscited by 1
  20. 2023AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehiclescited by 1
  21. 2024OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attackcited by 1
  22. 2025Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognitioncited by 1
  23. 2025Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representationcited by 1
  24. 2021Mitigating Gradient-based Adversarial Attacks via Denoising and Compressioncited by 0
  25. 2021Salient Feature Extractor for Adversarial Defense on Deep Neural Networkscited by 0
  26. 2021Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognitioncited by 0
  27. 2021NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbationscited by 0
  28. 2022A Perturbation Resistant Transformation and Classification System for Deep Neural Networkscited by 0
  29. 2023ATWM: Defense against adversarial malware based on adversarial trainingcited by 0
  30. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  31. 2023GMTR: Graph Matching Transformerscited by 0
  32. 2023Adversarial defense based on distribution transfercited by 0
  33. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  34. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  35. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  36. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  37. 2024On the Perturbed States for Transformed Input-robust Reinforcement Learningcited by 0
  38. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0

50 most cited of 57 All 57 (JSON)