Towards Feature Space Adversarial Attack
arXiv:2004.12385
Abstract
We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features that denote styles, including interpretable styles such as vivid colors and sharp outlines, and uninterpretable ones. It induces model misclassfication by injecting imperceptible style changes through an optimization procedure. We show that our attack can generate adversarial samples that are more natural-looking than the state-of-the-art unbounded attacks. The experiment also supports that existing pixel-space adversarial attack detection and defense techniques can hardly ensure robustness in the style related feature space.
arXiv commentAAAI 2021
References in corpus (10)
- Wide Residual Networks
- Theoretically Principled Trade-off between Robustness and Accuracy
- A Learned Representation For Artistic Style
- Adversarial Machine Learning at Scale
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
- Functional Adversarial Attacks
- Improving the Generalization of Adversarial Training with Domain Adaptation
- Unrestricted Adversarial Examples via Semantic Manipulation
- Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples