Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
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.
Code (1)
Tasks
Adversarial RobustnessPredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CausAdv: A Causal-based Framework for Detecting Adversarial Examples
Deep learning has led to tremendous success in many real-world applications of computer vision, thanks to sophisticated architectures such as Convolutional neural networks (CNNs). However, CNNs have been shown to be vuln…
Adversarial RobustnesscounterfactualCounterfactual ReasoningWhen Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks
Discovering and exploiting the causality in deep neural networks (DNNs) are crucial challenges for understanding and reasoning causal effects (CE) on an explainable visual model. "Intervention" has been widely used for r…
Causal InferenceVisual ReasoningAdversarial Visual Robustness by Causal Intervention
Adversarial training is the de facto most promising defense against adversarial examples. Yet, its passive nature inevitably prevents it from being immune to unknown attackers. To achieve a proactive defense, we need a m…
Adversarial RobustnessWhere and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
Deep neural networks (DNNs) have been demonstrated to be vulnerable to well-crafted \emph{adversarial examples}, which are generated through either well-conceived $\mathcal{L}_p$-norm restricted or unrestricted attacks. …
Adversarial AttackcounterfactualIDEA: Invariant Defense for Graph Adversarial Robustness
Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suffer from severe performance decline unde…
Adversarial Robustness