Deep Defense: Training DNNs with Improved Adversarial Robustness

2018/02/23 by Ziang Yan, Yiwen Guo, Yan, Ziang +3 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1803.00404

openalex publication_date 2018/02/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating imperceptibly perturbed image inputs (a.k.a., adversarial examples) to fool well-trained DNN classifiers into making arbitrary predictions. To address this problem, we propose a training recipe named "deep defense". Our core idea is to integrate an adversarial perturbation-based regularizer into the classification objective, such that the obtained models learn to resist potential attacks, directly and precisely. The whole optimization problem is solved just like training a recursive network. Experimental results demonstrate that our method outperforms training with adversarial/Parseval regularizations by large margins on various datasets (including MNIST, CIFAR-10 and ImageNet) and different DNN architectures. Code and models for reproducing our results are available at https://github.com/ZiangYan/deepdefense.pytorch

Citations

• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Parseval Networks: Improving Robustness to Adversarial Examples
• Deep Residual Learning for Image Recognition

Cited by

• Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era
• Generating 3D Adversarial Point Clouds
• A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities

Related

• Evaluating a Simple Retraining Strategy as a Defense Against Adversarial Attacks
• A Self-supervised Approach for Adversarial Robustness
• Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness
• Divide, Denoise, and Defend against Adversarial Attacks
• A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations