0

Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability Connection

Adversarial training enhances the interpretability and robustness of deep learning models, improving their feature learning and making them more resilient to attacks.

Year
2023
Venue
arXiv 2023
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2307.02500v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized to produce robust models - less vulnerable to adversarial attacks. It has been shown to make computer vision models more interpretable. Interpretability is as essential as robustness when we deploy the models to the real world. To prove the correlation between these two problems, we extensively examine the models using local feature-importance methods (SHAP, Integrated Gradients) and feature visualization techniques (Representation Inversion, Class Specific Image Generation). Standard models, compared to robust are more susceptible to adversarial attacks, and their learned representations are less meaningful to humans. Conversely, these models focus on distinctive regions of the images which support their predictions. Moreover, the features learned by the robust model are closer to the real ones.

Authors

1