×
Mar 17, 2023 · This paper proposes an elegant method to turn adversarial attacks into semantically meaningful perturbations, without modifying the classifiers to explain.
Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.
This repository contains the official code for the CVPR 2023 paper Adversarial Counterfactual Visual Explanations.
This paper proposes an elegant method to turn adversarial attacks into semantically meaningful perturbations, without modifying the classifiers to explain.
Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.
Mar 17, 2023 · Building on the robust learning literature, this paper proposes an elegant method to turn adversarial attacks into semantically meaningful ...
The key idea is to build attacks through a diffusion model to polish them, which allows studying the target model regardless of its robustification level, ...
The final result is the counterfactual explanation. Algorithm 1 Pre-explanation generation. Require: Diffusion Model D, Distance loss d and its reg- ularization ...
This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary ...
Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.