paper-with-me

Papers

Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball

2019-12-19 · CVPR 2021 1 · Andrew Elliott, Stephen Law, Chris Russell

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.

📄 PDF Abstract BibTeX arXiv:1912.09405

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactual

Methods 이 논문이 사용한 방법론

Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

2019-10-18 · Simran Kaur, Jeremy Cohen, Zachary C. Lipton

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 Robustness

Attack to Explain Deep Representation

2020-06-01 · CVPR 2020 6 · Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian

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 Manipulation

Wide Two-Layer Networks can Learn from Adversarial Perturbations

2024-10-31 · Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

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?

2021-06-24 · P Charantej Reddy, Aditya Siripuram, Sumohana S. Channappayya

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…

SSIM

Metrics and methods for robustness evaluation of neural networks with generative models

2020-03-04 · Igor Buzhinsky, Arseny Nerinovsky, Stavros Tripakis

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