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

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.

arXiv commentAccepted as Tutorial in CIKM 2021

References in corpus (10)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Adversarially Robust Generalization Requires More Data
• AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
• Lipschitz regularity of deep neural networks: analysis and efficient estimation
• A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
• A Safety Framework for Critical Systems Utilising Deep Neural Networks
• How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
• Towards the Quantification of Safety Risks in Deep Neural Networks
• Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks
• Improving Model Robustness with Latent Distribution Locally and Globally