mlsanityData to 7 Oct 2026

FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples

arXiv 2206.00924 ↗First posted 2 Jun 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In strong adversarial attacks against deep neural networks (DNN), the generated adversarial example will mislead the DNN-implemented classifier by destroying the output features of the last layer. To enhance the robustness of the classifier, in our paper, a Feature Analysis and Conditional Matching prediction distribution (FACM) model is proposed to utilize the features of intermediate layers to correct the classification. Specifically, we first prove that the intermediate layers of the classifier can still retain effective features for the original category, which is defined as the correction property in our paper. According to this, we propose the FACM model consisting of Feature Analysis (FA) correction module, Conditional Matching Prediction Distribution (CMPD) correction module and decision module. The FA correction module is the fully connected layers constructed with the output of the intermediate layers as the input to correct the classification of the classifier. The CMPD correction module is a conditional auto-encoder, which can not only use the output of intermediate layers as the condition to accelerate convergence but also mitigate the negative effect of adversarial example training with the Kullback-Leibler loss to match prediction distribution. Through the empirically verified diversity property, the correction modules can be implemented synergistically to reduce the adversarial subspace. Hence, the decision module is proposed to integrate the correction modules to enhance the DNN classifier's robustness. Specially, our model can be achieved by fine-tuning and can be combined with other model-specific defenses.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 71 references that are in the map. First posted on arXiv 2 Jun 2022.

Builds on

54 of 71 references.

References · 54

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Wide Residual Networkscited by 3,057
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
38 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  5. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  6. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  7. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  8. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  9. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  10. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  11. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  12. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  13. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  14. 2021Improving Robustness using Generated Datacited by 233
  15. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  16. 2020Bag of Tricks for Adversarial Trainingcited by 199
  17. 2021Data Augmentation Can Improve Robustnesscited by 193
  18. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  19. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  20. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  21. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  22. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  23. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  24. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  25. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  26. 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
  27. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  28. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  29. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  30. 2020Adversarial Robustness on In- and Out-Distribution Improves Explainabilitycited by 73
  31. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 73
  32. 2021A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustnesscited by 62
  33. 2020Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 61
  34. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 54
  35. 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
  36. 2021PRIME: A few primitives can boost robustness to common corruptionscited by 40
  37. 2021Defending Against Image Corruptions Through Adversarial Augmentationscited by 28
  38. 2018Adversarial Noise Layer: Regularize Neural Network By Adding Noisecited by 25

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.