Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

2021/08/24 by Wenjie Ruan, Ruan, Wenjie, Xinping Yi +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Bacillus and Francisella bacterial research #FOS: Computer and information sciences #Integrated Circuits and Semiconductor Failure Analysis #Machine Learning (cs.LG) #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2108.10451

Accepted as Tutorial in CIKM 2021

arxiv created 2021/08/24 · openalex publication_date 2021/08/24 · arxiv updated 2021/08/25 · openalex created_date 2021/08/30 · openalex updated_date 2026/08/03

Abstract

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples. This tutorial will particularly highlight state-of-the-art techniques in adversarial attacks and robustness verification of deep neural networks (DNNs). We will also introduce some effective countermeasures to improve the robustness of deep learning models, with a particular focus on adversarial training. We aim to provide a comprehensive overall picture about this emerging direction and enable the community to be aware of the urgency and importance of designing robust deep learning models in safety-critical data analytical applications, ultimately enabling the end-users to trust deep learning classifiers. We will also summarize potential research directions concerning the adversarial robustness of deep learning, and its potential benefits to enable accountable and trustworthy deep learning-based data analytical systems and applications.

Citations

• ImageNet Large Scale Visual Recognition Challenge
• Adversarially Robust Generalization Requires More Data
• Lipschitz regularity of deep neural networks: analysis and efficient estimation
• Making machine learning robust against adversarial inputs
• Towards the Quantification of Safety Risks in Deep Neural Networks
• How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
• Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks
• Improving Model Robustness with Latent Distribution Locally and Globally

Related

• Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
• Holistic Adversarial Robustness of Deep Learning Models
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey