ML-LOO: Detecting Adversarial Examples with Feature Attribution

Puyudi Yang
Puyudi Yang
Jianbo Chen
Jianbo Chen
Jane-Ling Wang
Jane-Ling Wang

national conference on artificial intelligence, 2020.

Cited by: 0|Bibtex|Views63|Links

Abstract:

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a significant difference in feature attributions of adversarially crafted examples from those of origi...More

Code:

Data:

Your rating :
0

 

Tags
Comments