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

arXiv: https://arxiv.org/abs/2606.23132 · HTML: https://mlsanity.com/paper/2606.23132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 46 of its 57 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [VLP: A Survey on Vision-Language Pre-training](https://mlsanity.com/paper/2202.09061/) (2022)
- [Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models](https://mlsanity.com/paper/2402.12336/) (2024)
- [Understanding Zero-Shot Adversarial Robustness for Large-Scale Models](https://mlsanity.com/paper/2212.07016/) (2022)
- [C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion](https://mlsanity.com/paper/2403.14119/) (2024)

## Abstract (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 directly adapt the corrupted visual representation itself. Prompt-based methods adapt the learnable text prompts, while input-space methods optimize pixels or padding at test time. These approaches can improve predictions, but they do so through an indirect and expensive optimization path. We propose Test-time Visual Subspace Steering (T-VSS), a lightweight defense that performs test-time adaptation directly in the visual feature space. T-VSS first builds a sample-specific low-rank subspace from multi-view feature residuals anchored at the attacked image. It then learns a shared feature correction within this subspace using reliability-weighted entropy minimization. By constraining adaptation to a compact visual geometry, T-VSS steers attacked features toward more stable and discriminative predictions while avoiding noisy full-space updates. Experiments on fine-grained, ImageNet, and ImageNet-OOD benchmarks show that T-VSS improves adversarial robustness while maintaining competitive clean accuracy and better efficiency than prior test-time adaptations.