A Robust Classification-autoencoder to Defend Outliers and Adversaries
Not on the map. Why?
Abstract (arXiv)
In this paper, a robust classification-autoencoder (CAE) is proposed, which has strong ability to recognize outliers and defend adversaries. The main idea is to change the autoencoder from an unsupervised learning model into a classifier, where the encoder is used to compress samples with different labels into disjoint compression spaces and the decoder is used to recover samples from their compression spaces. The encoder is used both as a compressed feature learner and as a classifier, and the decoder is used to decide whether the classification given by the encoder is correct by comparing the input sample with the output. Since adversary samples are seemingly inevitable for the current DNN framework, the list classifier to defend adversaries is introduced based on CAE, which outputs several labels and the corresponding samples recovered by the CAE. Extensive experimental results are used to show that the CAE achieves state of the art to recognize outliers by finding almost all outliers; the list classifier gives near lossless classification in the sense that the output list contains the correct label for almost all adversaries and the size of the output list is reasonably small.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 30 Jun 2021.
Builds on
24 of 45 references.
References · 24
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
- 2017Evasion Attacks against Machine Learning at Test Timecited by 686
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2017Mitigating Adversarial Effects Through Randomizationcited by 382
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
12 more
- 2019Deep Learning for Anomaly Detection: A Surveycited by 357
- 2018Certified Defenses against Adversarial Examplescited by 305
- 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
- 2015Semi-Supervised Learning with Ladder Networkscited by 246
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
- 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
- 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
- 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
- 2018Geometric Understanding of Deep Learningcited by 41
- 2020Towards Robust Pattern Recognition: A Reviewcited by 31
- 2020Recent Advances in Understanding Adversarial Robustness of Deep Neural Networkscited by 3
Built on by
Citing papers per year: 2021: 1.
1 paper.