paper-with-me

홈 › Papers

Vulnerability-Aware Instance Reweighting For Adversarial Training

2023-07-14 · Olukorede Fakorede, Ashutosh Kumar Nirala, Modeste Atsague, Jin Tian

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most variants of AT algorithms treat every training example equally. However, recent works have shown that better performance is achievable by treating them unequally. In addition, it has been observed that AT exerts an uneven influence on different classes in a training set and unfairly hurts examples corresponding to classes that are inherently harder to classify. Consequently, various reweighting schemes have been proposed that assign unequal weights to robust losses of individual examples in a training set. In this work, we propose a novel instance-wise reweighting scheme. It considers the vulnerability of each natural example and the resulting information loss on its adversarial counterpart occasioned by adversarial attacks. Through extensive experiments, we show that our proposed method significantly improves over existing reweighting schemes, especially against strong white and black-box attacks.

📄 PDF Abstract BibTeX arXiv:2307.07167

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget

2024-03-06 · Olukorede Fakorede, Modeste Atsague, Jin Tian

Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fix…

Probabilistic Margins for Instance Reweighting in Adversarial Training

2021-06-15 · NeurIPS 2021 12 · Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu 외

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However…

Adversarial Robustness

δ-SAM: Sharpness-Aware Minimization with Dynamic Reweighting

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adve…

Sharpness-Aware Minimization with Dynamic Reweighting

2021-12-16 · Wenxuan Zhou, Fangyu Liu, huan zhang, Muhao Chen

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adve…

Natural Language Understanding

Local Reweighting for Adversarial Training

2021-06-30 · Ruize Gao, Feng Liu, Kaiwen Zhou, Gang Niu 외

Instances-reweighted adversarial training (IRAT) can significantly boost the robustness of trained models, where data being less/more vulnerable to the given attack are assigned smaller/larger weights during training. Ho…