Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
In this paper, the bias classifier is introduced, that is, the bias part of a DNN with Relu as the activation function is used as a classifier. The work is motivated by the fact that the bias part is a piecewise constant function with zero gradient and hence cannot be directly attacked by gradient-based methods to generate adversaries, such as FGSM. The existence of the bias classifier is proved and an effective training method for the bias classifier is given. It is proved that by adding a proper random first-degree part to the bias classifier, an information-theoretically safe classifier against the original-model gradient attack is obtained in the sense that the attack will generate a totally random attacking direction. This seems to be the first time that the concept of information-theoretically safe classifier is proposed. Several attack methods for the bias classifier are proposed and numerical experiments are used to show that the bias classifier is more robust than DNNs with similar size against these attacks in most cases.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 8 Nov 2021.
Builds on
29 of 42 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 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
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
17 more
- 2019Adversarial Training for Free!cited by 638
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2017Mitigating Adversarial Effects Through Randomizationcited by 382
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
- 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
- 2017The Space of Transferable Adversarial Examplescited by 156
- 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
- 2020Towards Robust Pattern Recognition: A Reviewcited by 31
- 2020MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Anglescited by 15
- 2018Robustness via Deep Low-Rank Representationscited by 11
- 2020Recent Advances in Understanding Adversarial Robustness of Deep Neural Networkscited by 3
- 2021A Robust Classification-autoencoder to Defend Outliers and Adversariescited by 1
Built on by
Citing papers per year: 2022: 2.
2 papers.