Soft Adversarial Training Can Retain Natural Accuracy

Abhijith Sharma, Apurva Narayan

2022

Abstract

Adversarial training for neural networks has been in the limelight in recent years. The advancement in neural network architectures over the last decade has led to significant improvement in their performance. It sparked an interest in their deployment for real-time applications. This process initiated the need to understand the vulnerability of these models to adversarial attacks. It is instrumental in designing models that are robust against adversaries. Recent works have proposed novel techniques to counter the adversaries, most often sacrificing natural accuracy. Most suggest training with an adversarial version of the inputs, constantly moving away from the original distribution. The focus of our work is to use abstract certification to extract a subset of inputs for (hence we call it ’soft’) adversarial training. We propose a training framework that can retain natural accuracy without sacrificing robustness in a constrained setting. Our framework specifically targets moderately critical applications which require a reasonable balance between robustness and accuracy. The results testify to the idea of soft adversarial training for the defense against adversarial attacks. At last, we propose the scope of future work for further improvement of this framework.

Paper Citation

in Harvard Style

Sharma A. and Narayan A. (2022). Soft Adversarial Training Can Retain Natural Accuracy. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-547-0, pages 621-628. DOI: 10.5220/0010871000003116

in Bibtex Style

@conference{icaart22,
author={Abhijith Sharma and Apurva Narayan},
title={Soft Adversarial Training Can Retain Natural Accuracy},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2022},
pages={621-628},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010871000003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Soft Adversarial Training Can Retain Natural Accuracy
SN - 978-989-758-547-0
AU - Sharma A.
AU - Narayan A.
PY - 2022
SP - 621
EP - 628
DO - 10.5220/0010871000003116