French scholars: the explicability of counter attack under optimal transmission theory

This article shares papers 『When adversarial attacks become interpretable counterfactual explanations』, The explicability of counter attack under optimal transmission theory .

 

The details are as follows ：

The author is from the third University of Toulouse in France and IRT Saint-Exupéry Research institute, .

Thesis link ：https://arxiv.org/pdf/2206.06854.pdf

 

This paper is a theoretical article on countering attacks , The author provides a very reliable explanation for countering attacks . At present, the optimal transmission theory is a very popular direction in the deep learning theory , The author analyzes the phenomenon of anti attack from the perspective of optimal transmission theory . When learning a neural network with dual loss of optimal transmission problem , The gradient of the model is the direction of the optimal transmission scheme , It is also the direction closest to the confrontation sample .
Moving along the gradient to the decision boundary is no longer a counter attack , It's a counterfactual explanation , That is, it can be seen as explicitly transferring from one class to another . Interpretable by AI A large number of experiments on measurement can find , The simple saliency mapping method applied to the optimal transmission network is a reliable explanation , And it is superior to the latest interpretation method in the unconstrained model .