Test-Time Adaptation and Adversarial Robustness

2021-01-01 · Xi Wu, Yang Guo, Tianqi Li, Jiefeng Chen, Qicheng Lao, YIngyu Liang, Somesh Jha

This paper studies test-time adaptation in the context of adversarial robustness. We first formulate an adversarial threat model for test-time adaptation, where the defender may have a unique advantage as the adversarial game becomes a maximin game, instead of a minimax game as in the classic adversarial robustness threat model. We then study whether the maximin threat model admits more ``good solutions'' than the minimax threat model, and is thus \emph{strictly weaker}. On the positive side, we show that, if one is allowed to access the training data, then Domain Adversarial Neural Networks (${\sf DANN}$), an algorithm designed for unsupervised domain adaptation, can provide nontrivial robustness in the test-time maximin threat model against strong transfer attacks and adaptive fixed point attacks. This is somewhat surprising since ${\sf DANN}$ is not designed specifically for adversarial robustness (e.g. against norm-based attacks), and provides no robustness in the minimax model. On the negative side, we show that recent data-oblivious test-time adaptations, in contrast to ${\sf DANN}$, can be easily attacked. We take a step to discuss moving towards adversarially robust test-time adaptation and examine its various implications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness Domain Adaptation Test-time Adaptation Unsupervised Domain Adaptation

T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models

2026-06-22 · Jaehyuk Jang, Minseok Seo. Seungju Cho, Kangwook Ko, Changick Kim arxiv

Vision-language models (VLMs) achieve strong zero-shot recognition, but they remain highly vulnerable to adversarial perturbations. Recent test-time adaptations improve robustness without retraining, but they do not dire…

Adversarial Robustness Test-time Adaptation

TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models

2025-12-18 · Zhiwei Li, Yitian Pang, Weining Wang, Zhenan Sun 외 arxiv

Vision-Language Models (VLMs), such as CLIP, have achieved impressive zero-shot recognition performance but remain highly susceptible to adversarial perturbations, posing significant risks in safety-critical scenarios. P…

Adversarial Robustness Test-time Adaptation

Learning Robustness at Test-Time from a Non-Robust Teacher

2026-04-13 · Stefano Bianchettin, Giulio Rossolini, Giorgio Buttazzo arxiv

Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for …

Adversarial Robustness

Robustifying Vision-Language Models via Test-Time Prompt Adaptation

2026-07-10 · Xingyu Zhu, Huanshen Wu, Shuo Wang, Beier Zhu 외 arxiv

Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing test-time adaptation methods typically rely…

Zero-shot Generalization Adversarial Robustness Test-time Adaptation

Adversarial Defense in Vision-Language Models: An Overview

2026-01-18 · Xiaowei Fu, Lei Zhang arxiv

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and sy…

Test-time Adaptation Adversarial Defense