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 itself susceptible to adversarial attacks. In this paper, we theoretically show that with a proper measurement of interpretation, it is actually difficult to prevent prediction-evasion adversarial attacks from causing interpretation discrepancy, as confirmed by experiments on MNIST, CIFAR-10 and Restricted ImageNet. Spurred by that, we develop an interpretability-aware defensive scheme built only on promoting robust interpretation (without the need for resorting to adversarial loss minimization). We show that our defense achieves both robust classification and robust interpretation, outperforming state-of-the-art adversarial training methods against attacks of large perturbation in particular.
Code (1)
Tasks
Adversarial RobustnessClassificationGeneral ClassificationNetwork InterpretationRobust classificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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 t…
Adversarial RobustnessInterpretability 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 MakingOn the interplay of adversarial robustness and architecture components: patches, convolution and attention
In recent years novel architecture components for image classification have been developed, starting with attention and patches used in transformers. While prior works have analyzed the influence of some aspects of archi…
Adversarial Robustnessimage-classificationImage ClassificationRobust Text Classification: Analyzing Prototype-Based Networks
Downstream applications often require text classification models to be accurate and robust. While the accuracy of the state-of-the-art Language Models (LMs) approximates human performance, they often exhibit a drop in pe…
Adversarial AttackClassificationClusteringSentence+2A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures
Convolutional Neural Networks (CNNs) achieve strong image classification performance but lack interpretability and are vulnerable to adversarial attacks. Neuro-fuzzy hybrids such as DCNFIS replace fully connected CNN cla…
Adversarial RobustnessImage Classification