Adversarial Parameter Defense by Multi-Step Risk Minimization
Not on the map. Why?
Abstract (arXiv)
Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show that deep neural networks also exhibit vulnerability to parameter corruptions. The vulnerability of model parameters is of crucial value to the study of model robustness and generalization. In this work, we introduce the concept of parameter corruption and propose to leverage the loss change indicators for measuring the flatness of the loss basin and the parameter robustness of neural network parameters. On such basis, we analyze parameter corruptions and propose the multi-step adversarial corruption algorithm. To enhance neural networks, we propose the adversarial parameter defense algorithm that minimizes the average risk of multiple adversarial parameter corruptions. Experimental results show that the proposed algorithm can improve both the parameter robustness and accuracy of neural networks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 7 Sep 2021.
Builds on
35 of 52 references.
References · 35
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
23 more
- 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
- 2017Exploring Generalization in Deep Learningcited by 595
- 2015Sequence Level Training with Recurrent Neural Networkscited by 568
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 357
- 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
- 2020Weight Poisoning Attacks on Pre-trained Modelscited by 318
- 2018Stronger generalization bounds for deep nets via a compression approachcited by 306
- 2019A backdoor attack against LSTM-based text classification systemscited by 214
- 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
- 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2016Sequence-to-Sequence Learning as Beam-Search Optimizationcited by 126
- 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
- 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 112
- 2019Better Algorithms for Stochastic Bandits with Adversarial Corruptionscited by 91
- 2020Regularizing Neural Networks via Adversarial Model Perturbationcited by 78
- 2020Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruptioncited by 26
- 2021Improved Corruption Robust Algorithms for Episodic Reinforcement Learningcited by 20
- 2020Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planescited by 15
- 2018Adversarial Defense via Data Dependent Activation Function and Total Variation Minimizationcited by 9
- 2019LCA: Loss Change Allocation for Neural Network Trainingcited by 9
- 2019Adversarial Defense via Local Flatness Regularizationcited by 9
- 2020Gradient ℓ1 Regularization for Quantization Robustnesscited by 4
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.