On Saliency Maps and Adversarial Robustness
A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries. Works have shown that adversarially trained models exhibit more interpretable saliency maps than their non-robust counterparts, and that this behavior can be quantified by considering the alignment between input image and saliency map. In this work, we provide a different perspective to this coupling, and provide a method, Saliency based Adversarial training (SAT), to use saliency maps to improve adversarial robustness of a model. In particular, we show that using annotations such as bounding boxes and segmentation masks, already provided with a dataset, as weak saliency maps, suffices to improve adversarial robustness with no additional effort to generate the perturbations themselves. Our empirical results on CIFAR-10, CIFAR-100, Tiny ImageNet and Flower-17 datasets consistently corroborate our claim, by showing improved adversarial robustness using our method. saliency maps. We also show how using finer and stronger saliency maps leads to more robust models, and how integrating SAT with existing adversarial training methods, further boosts performance of these existing methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach
Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehens…
Decision MakingImproving the Interpretability of fMRI Decoding using Deep Neural Networks and Adversarial Robustness
Deep neural networks (DNNs) are being increasingly used to make predictions from functional magnetic resonance imaging (fMRI) data. However, they are widely seen as uninterpretable "black boxes", as it can be difficult t…
Adversarial RobustnessOn the Connection Between Adversarial Robustness and Saliency Map Interpretability
Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts. We a…
Adversarial RobustnessDANCE: Enhancing saliency maps using decoys
Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image cla…
Adversarial AttackDecoy-enhanced Saliency Maps
Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image cla…