paper-with-me

홈 › Papers

Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples

2022-05-01 · Findings (ACL) 2022 5 · Jianhan Xu, Cenyuan Zhang, Xiaoqing Zheng, Linyang Li, Cho-Jui Hsieh, Kai-Wei Chang, Xuanjing Huang

Most of the existing defense methods improve the adversarial robustness by making the models adapt to the training set augmented with some adversarial examples. However, the augmented adversarial examples may not be natural, which might distort the training distribution, resulting in inferior performance both in clean accuracy and adversarial robustness. In this study, we explore the feasibility of introducing a reweighting mechanism to calibrate the training distribution to obtain robust models. We propose to train text classifiers by a sample reweighting method in which the example weights are learned to minimize the loss of a validation set mixed with the clean examples and their adversarial ones in an online learning manner. Through extensive experiments, we show that there exists a reweighting mechanism to make the models more robust against adversarial attacks without the need to craft the adversarial examples for the entire training set.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification

2019-05-27 · Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde

The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to …

ClassificationGeneral ClassificationRobust classificationvalid

Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees

2025-10-14 · Yiming Zhang, Chester Holtz, Gal Mishne, Alex Cloninger arxiv

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, ye…

Learning with noisy labels

Probabilistically robust conformal prediction

2023-07-31 · Subhankar Ghosh, Yuanjie Shi, Taha Belkhouja, Yan Yan 외

Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate…

Conformal PredictionPrediction

Benign Overfitting in Adversarially Robust Linear Classification

2021-12-31 · Jinghui Chen, Yuan Cao, Quanquan Gu

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon…

Classification

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

2021-12-09 · Shubhi Shukla, Subhadeep Dalui, Manaar Alam, Shubhajit Datta 외

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to misle…

DiversityImage Classification