HOME Board
Notice

Notice

Hit 1699
Subject [CVPR 2023] Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression (by Junho Kim and Byung-Kwan Lee) is accepted in CVPR 2023
Name IVY Lab. KAIST
Date 2023-02-28
Title: Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression


Authors: Junho Kim*, Byung-Kwan Lee*, and Yong Man Ro (* equally contributed)


The origin of adversarial examples is still inexplicable in research fields, and it arouses arguments from various viewpoints, albeit comprehensive investigations. In this paper, we propose a way of delving into the unexpected vulnerability in adversarially trained networks from a causal perspective, namely adversarial instrumental variable (IV) regression. By deploying it, we estimate the causal relation of adversarial prediction under an unbiased environment dissociated from unknown confounders. Our approach aims to demystify inherent causal features on adversarial examples by leveraging a zero-sum optimization game between a casual feature estimator (i.e., hypothesis model) and worst-case counterfactuals (i.e., test function) disturbing to find causal features. Through extensive analyses, we demonstrate that the estimated causal features are highly related to the correct prediction for adversarial robustness, and the counterfactuals exhibit extreme features significantly deviating from the correct prediction. In addition, we present how to effectively inoculate CAusal FEatures (CAFE) into defense networks for improving adversarial robustness.


IMAGE VIDEO SYSTEM (IVY.) KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY (KAIST), CVPR 2023