TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models

• URL: http://arxiv.org/abs/2605.17577v1
• Date: Sun, 17 May 2026 18:07:08 GMT
• Title: TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
• Abstract summary: Large-scale pre-trained Vision-Language models (VLMs) exhibit strong zero-shot generalization, yet are highly vulnerable to imperceptible adversarial perturbations.<n>To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense.
• Score: 76.92890872338235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world deployment. To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense. Building upon our prior Test-Time Adversarial Prompt Tuning (TAPT), TAME introduces an architectural reformulation by replacing TAPT's single adaptive prompt with an input-conditioned Mixture-of-Experts (MoE) framework, enabling more expressive and adaptive defense. Specifically, TAME maintains a bank of learnable expert prompts and employs an input-dependent routing mechanism to aggregate a customized prompt mixture for each unlabeled test sample at inference time. This test-time defense mechanism is driven by three unsupervised objectives: (1) multi-view prediction entropy minimization, (2) layer-wise alignment of visual token statistics to precomputed clean and adversarial reference distributions, and (3) MoE regularization for balanced expert utilization and prompt diversity. We evaluated TAME on 11 benchmark datasets, including ImageNet and 10 additional zero-shot datasets. The results show that TAME improves the zero-shot adversarial robustness of the original CLIP by at least 49.1% under AutoAttack while largely preserving generalization on clean samples. TAME also consistently outperforms existing adversarial prompt tuning methods across multiple prompt designs, yielding an average robustness gain of at least 30.2%.

Related papers

• Robustifying Vision-Language Models via Test-Time Prompt Adaptation [23.05168102474528]
  We propose RITA, a test-tIme prompt-TAdaptation framework that shifts from sample-level estimates to distribution-level alignment.<n>Specifically, RITA employs optimal transport to align the distribution of augmented visual features with textual prototypes, mitigating adversarial outliers and rectifying cross-modal semantic misalignment.
  arXiv  Detail & Related papers  (2026-07-10T14:19:42Z)
• DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models [78.62380562116135]
  We propose DynT2I-Eval, a fully automated dynamic evaluation framework for text-to-image (T2I) models.<n>It constructs a structured visual semantic space from long-form descriptions, decomposing prompts into controllable dimensions.<n>DynT2I-Eval evaluates model performance across text alignment, perceptual quality, and aesthetics.
  arXiv  Detail & Related papers  (2026-05-07T12:53:51Z)
• Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP [68.44229678548298]
  Contrastive Spectral Rectification (CSR) is an efficient test-time defense against adversarial examples.<n>CSR outperforms the SOTA by an average of 18.1% against strong AutoAttack.<n>CSR exhibits broad applicability across diverse visual tasks.
  arXiv  Detail & Related papers  (2026-01-27T05:24:45Z)
• TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models [32.85951917559796]
  We propose Test-Time Padding (TTP), a lightweight defense framework that performs adversarial detection followed by targeted adaptation at inference.<n>TTP consistently surpasses state-of-the-art test-time defenses, delivering substantial improvements in adversarial robustness without compromising clean accuracy.
  arXiv  Detail & Related papers  (2025-12-18T13:34:14Z)
• Test-Time Consistency in Vision Language Models [26.475993408532304]
  Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks.<n>Recent benchmarks, such as MM-R3, highlight that even state-of-the-art VLMs can produce divergent predictions across semantically equivalent inputs.<n>We propose a simple and effective test-time consistency framework that enhances semantic consistency without supervised re-training.
  arXiv  Detail & Related papers  (2025-06-27T17:09:44Z)
• Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning [1.3680468021400563]
  Few-shot adaptation remains a core challenge for vision-language models (VLMs)<n>We propose PromptFuseNL, a unified framework that enhances few-shot generalization by combining predictive prompt tuning with dual-branch positive and negative learning.
  arXiv  Detail & Related papers  (2025-05-16T23:39:34Z)
• TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models [53.91006249339802]
  We propose a novel defense method called Test-Time Adversarial Prompt Tuning (TAPT) to enhance the inference robustness of CLIP against visual adversarial attacks. TAPT is a test-time defense method that learns defensive bimodal (textual and visual) prompts to robustify the inference process of CLIP. We evaluate the effectiveness of TAPT on 11 benchmark datasets, including ImageNet and 10 other zero-shot datasets.
  arXiv  Detail & Related papers  (2024-11-20T08:58:59Z)
• Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection [9.241737058291823]
  Adrial training methods generate independent initial perturbation for adversarial samples from a simple uniform distribution. We propose a simple yet effective training framework called Batch-in-Batch to enhance models. We show that models trained within the BB framework consistently have higher adversarial accuracy across various adversarial settings.
  arXiv  Detail & Related papers  (2024-06-06T13:34:43Z)
• Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation [56.70910056845503]
  Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner.<n>Previous MM-TTA methods for 3D segmentation suffer from two major limitations: 1) unstable frame-wise predictions caused by temporal inconsistency, and 2) consistently incorrect predictions that violate the assumption of reliable modality guidance.<n>This work introduces a comprehensive two-fold framework: Latte++ that better suppresses the unstable frame-wise predictions with more informative geometric correspondences, and Interactive Test-Time Adaptation (ITTA), a flexible add-on to empower effortless human feedback
  arXiv  Detail & Related papers  (2024-03-11T06:56:08Z)
• Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models [107.05966685291067]
  We propose test-time prompt tuning (TPT) to learn adaptive prompts on the fly with a single test sample. TPT improves the zero-shot top-1 accuracy of CLIP by 3.6% on average. In evaluating cross-dataset generalization with unseen categories, TPT performs on par with the state-of-the-art approaches that use additional training data.
  arXiv  Detail & Related papers  (2022-09-15T17:55:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.