paper-with-me

Papers

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation

2023-09-21 · NeurIPS 2023 11

Gradual Domain Adaptation (GDA), in which the learner is provided with additional intermediate domains, has been theoretically and empirically studied in many contexts. Despite its vital role in security-critical scenarios, the adversarial robustness of the GDA model remains unexplored. In this paper, we adopt the effective gradual self-training method and replace vanilla self-training with adversarial self-training (AST). AST first predicts labels on the unlabeled data and then adversarially trains the model on the pseudo-labeled distribution. Intriguingly, we find that gradual AST improves not only adversarial accuracy but also clean accuracy on the target domain. We reveal that this is because adversarial training (AT) performs better than standard training when the pseudo-labels contain a portion of incorrect labels. Accordingly, we first present the generalization error bounds for gradual AST in a multiclass classification setting. We then use the optimal value of the Subset Sum Problem to bridge the standard error on a real distribution and the adversarial error on a pseudo-labeled distribution. The result indicates that AT may obtain a tighter bound than standard training on data with incorrect pseudo-labels. We further present an example of a conditional Gaussian distribution to provide more insights into why gradual AST can improve the clean accuracy for GDA.

📄 PDF Abstract BibTeX

Code (1)

whustone007/ast_gda 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Gradual Self-Training Gradual self-training is a method for semi-supervised domain adaptation. The goal is to adapt an initial classifier trained on a source domain given only unlabeled data that…

Similar Papers 제목 키워드 기반

Improving Adversarial Defense with Self-supervised Test-time Fine-tuning

2021-09-29 · Zhichao Huang, Chen Liu, Mathieu Salzmann, Sabine Süsstrunk 외

Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples. In thi…

Adversarial Defense

The Impact of Scaling Training Data on Adversarial Robustness

2025-09-30 · Marco Zimmerli, Andreas Plesner, Till Aczel, Roger Wattenhofer arxiv

Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-t…

Adversarial RobustnessContrastive Learning

Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning…

Adversarial AttackContrastive Learning

Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks

2021-07-15 · Findings (NAACL) 2022 7 · Zhao Meng, Yihan Dong, Mrinmaya Sachan, Roger Wattenhofer

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning…

Adversarial AttackContrastive LearningLanguage Modelling

Improving out-of-distribution generalization via multi-task self-supervised pretraining

2020-03-30 · Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar 외

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are compara…

Adversarial RobustnessDomain GeneralizationFew-Shot LearningMulti-Task Learning+2