When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks

Abstract

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 recognizing a causal relation ontologically. In this paper, we propose a causal inference framework for visual reasoning via do-calculus. To study the intervention effects on pixel-level features for causal reasoning, we introduce pixel-wise masking and adversarial perturbation. In our framework, CE is calculated using features in a latent space and perturbed prediction from a DNN-based model. We further provide the first look into the characteristics of discovered CE of adversarially perturbed images generated by gradient-based methods \footnote{~~https://github.com/jjaacckkyy63/Causal-Intervention-AE-wAdvImg}. Experimental results show that CE is a competitive and robust index for understanding DNNs when compared with conventional methods such as class-activation mappings (CAMs) on the Chest X-Ray-14 dataset for human-interpretable feature(s) (e.g., symptom) reasoning. Moreover, CE holds promises for detecting adversarial examples as it possesses distinct characteristics in the presence of adversarial perturbations.

arXiv commentNoted our camera-ready version has changed the title. "When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks" as the v3 official paper title in IEEE Proceeding. Please use it in your formal reference. Accepted at IEEE ICIP 2019. Pytorch code has released on https://github.com/jjaacckkyy63/Causal-Intervention-AE-wAdvImg

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Counterfactual Fairness
• Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations
• Explaining Deep Learning Models using Causal Inference

Cited by in corpus (5)

• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
• Treatment Learning Causal Transformer for Noisy Image Classification
• LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
• Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning
• Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding