Visual Interpretability Alone Helps Adversarial Robustness
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks. In this paper, we theoretically show that with the correct measurement of interpretation, it is actually difficult to hide adversarial examples, as confirmed by experiments on MNIST, CIFAR-10 and Restricted ImageNet. Spurred by that, we develop a novel defensive scheme built only on robust interpretation (without resorting to adversarial loss minimization). We show that our defense achieves similar classification robustness to state-of-the-art robust training methods while attaining higher interpretation robustness under various settings of adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Proper Network Interpretability Helps Adversarial Robustness in Classification
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itse…
Adversarial RobustnessClassificationGeneral ClassificationNetwork Interpretation+1On Fragile Features and Batch Normalization in Adversarial Training
Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In the context of robustness against …
Adversarial RobustnessBridging Adversarial Robustness and Gradient Interpretability
Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversa…
Adversarial RobustnessOvercoming Adversarial Attacks for Human-in-the-Loop Applications
Including human analysis has the potential to positively affect the robustness of Deep Neural Networks and is relatively unexplored in the Adversarial Machine Learning literature. Neural network visual explanation maps h…
Interpretability and Transparency-Driven Detection and Transformation of Textual Adversarial Examples (IT-DT)
Transformer-based text classifiers like BERT, Roberta, T5, and GPT-3 have shown impressive performance in NLP. However, their vulnerability to adversarial examples poses a security risk. Existing defense methods lack int…
Decision Making