Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball
We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are semi-sparse alterations that highlight objects and regions of interest while leaving the background unaltered. As a semantically meaningful adverse perturbations, it forms a bridge between counterfactual explanations and adversarial perturbations in the space of images. We evaluate our approach on several standard explainability benchmarks, namely, weak localization, insertion deletion, and the pointing game demonstrating that perceptually regularized counterfactuals are an effective explanation for image-based classifiers.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?
For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2…
Adversarial RobustnessAttack to Explain Deep Representation
Deep visual models are susceptible to extremely low magnitude perturbations to input images. Though carefully crafted, the perturbation patterns generally appear noisy, yet they are able to perform controlled manipulatio…
Image GenerationImage ManipulationWide Two-Layer Networks can Learn from Adversarial Perturbations
Adversarial examples have raised several open questions, such as why they can deceive classifiers and transfer between different models. A prevailing hypothesis to explain these phenomena suggests that adversarial pertur…
Can Perceptual Guidance Lead to Semantically Explainable Adversarial Perturbations?
It is well known that carefully crafted imperceptible perturbations can cause state-of-the-art deep learning classification models to misclassify. Understanding and analyzing these adversarial perturbations play a crucia…
SSIMMetrics and methods for robustness evaluation of neural networks with generative models
Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and meth…
Adversarial Robustnessimage-classificationImage Classification