Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xin, Wang, Yixu, Zhang, Jiaming, Wang, Ruofan, Yu, Jiaqi, Chen, Kai, Chen, Jingjing, Ma, Xingjun, Jiang, Yu-Gang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
by: Wang, Xin, et al.
Published: (2024)

Adversarial Prompt Tuning for Vision-Language Models
by: Zhang, Jiaming, et al.
Published: (2023)

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
by: Wang, Xin, et al.
Published: (2024)

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
by: Zhang, Jiaming, et al.
Published: (2025)

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
by: Zhai, Kun, et al.
Published: (2025)

Adversarial Prompt Distillation for Vision-Language Models
by: Luo, Lin, et al.
Published: (2024)

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
by: Wang, Ruofan, et al.
Published: (2025)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
by: Wang, Ruofan, et al.
Published: (2024)

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
by: Sun, Ye, et al.
Published: (2026)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
by: Li, Juncheng, et al.
Published: (2025)

EnJa: Ensemble Jailbreak on Large Language Models
by: Zhang, Jiahao, et al.
Published: (2024)

White-box Multimodal Jailbreaks Against Large Vision-Language Models
by: Wang, Ruofan, et al.
Published: (2024)

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
by: Yu, Jiaqi, et al.
Published: (2026)

BadPatch: Diffusion-Based Generation of Physical Adversarial Patches
by: Wang, Zhixiang, et al.
Published: (2024)

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
by: Song, Jiaxin, et al.
Published: (2025)

Efficient Test-Time Prompt Tuning for Vision-Language Models
by: Zhu, Yuhan, et al.
Published: (2024)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
by: Wang, Yixu, et al.
Published: (2025)

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
by: Wang, Ruofan, et al.
Published: (2025)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
by: Wang, Xin, et al.
Published: (2025)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
by: Li, Teng, et al.
Published: (2025)

TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
by: Cheng, Yu, et al.
Published: (2026)

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
by: Sheng, Lijun, et al.
Published: (2025)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
by: Zheng, Weijie, et al.
Published: (2024)

MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language Models
by: Zhao, Shiji, et al.
Published: (2025)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
by: Li, Jiayu, et al.
Published: (2025)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
by: Wang, Yixu, et al.
Published: (2025)

Towards Context-Invariant Safety Alignment for Large Language Models
by: Wang, Yixu, et al.
Published: (2026)

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
by: Huang, Yixu, et al.
Published: (2026)

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
by: Li, Yige, et al.
Published: (2024)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
by: Zi, Bojia, et al.
Published: (2021)

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models
by: Luo, Jun, et al.
Published: (2024)

Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
by: Song, Fei, et al.
Published: (2025)

LeakyCLIP: Extracting Training Data from CLIP
by: Chen, Yunhao, et al.
Published: (2025)

Adapted-MoE: Mixture of Experts with Test-Time Adaption for Anomaly Detection
by: Lei, Tianwu, et al.
Published: (2024)

Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning
by: Gou, Yunhao, et al.
Published: (2023)

HoneypotNet: Backdoor Attacks Against Model Extraction
by: Wang, Yixu, et al.
Published: (2025)

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models
by: Chen, Yang, et al.
Published: (2024)

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
by: Wang, Yixu, et al.
Published: (2025)

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
by: Yu, Jiazuo, et al.
Published: (2024)