Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks

2021/01/16 by Jia Liu, Liu, Jia, Yaochu Jin +1
Computer Science · Materials Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.2101.06507

openalex publication_date 2021/01/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of adversarial attacks. It is practically impossible, however, to predict beforehand which type of attacks a machine learn model may suffer from. To address this challenge, we propose to search for deep neural architectures that are robust to five types of well-known adversarial attacks using a multi-objective evolutionary algorithm. To reduce the computational cost, a normalized error rate of a randomly chosen attack is calculated as the robustness for each newly generated neural architecture at each generation. All non-dominated network architectures obtained by the proposed method are then fully trained against randomly chosen adversarial attacks and tested on two widely used datasets. Our experimental results demonstrate the superiority of optimized neural architectures found by the proposed approach over state-of-the-art networks that are widely used in the literature in terms of the classification accuracy under different adversarial attacks.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Wide Residual Networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• A study of the effect of JPG compression on adversarial images
• Neural Architecture Search with Reinforcement Learning
• DARTS: Differentiable Architecture Search
• On the Convergence and Robustness of Adversarial Training
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Efficient Architecture Search by Network Transformation
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Once-for-All: Train One Network and Specialize it for Efficient Deployment
• Fast is better than free: Revisiting adversarial training

Related

• Differentiable Search of Accurate and Robust Architectures
• Evolving Robust Neural Architectures to Defend from Adversarial Attacks
• Effective, Efficient and Robust Neural Architecture Search
• Towards Accurate and Robust Architectures via Neural Architecture Search
• A³D: A Platform of Searching for Robust Neural Architectures and Efficient Adversarial Attacks