arXiv Machine Learning July 13, 2026 By Xingyu Zhu, Huanshen Wu, Shuo Wang, Beier Zhu, Jiannan Ge, Jiaheng Zhang, Long Chen

Robustifying Vision-Language Models via Test-Time Prompt Adaptation

Read the original on arXiv Machine Learning →

arXiv:2607. 09450v1 Announce Type: cross Abstract: Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 8

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.

By Sunoh Kim, Daeho Um

llms efficiency multimodal benchmarks safety

Hugging Face Trending Papers

Jun 2

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.

llms rag fine-tuning multimodal safety

arXiv AI

Jul 22

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.

By Sibo Wang, Jie Zhang, Shiguang Shan, Xilin Chen, Wen Gao

llms nlp fine-tuning multimodal benchmarks safety

arXiv AI

Jun 10

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.

By Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu

llms multimodal safety

Hugging Face Trending Papers

Jul 21

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.

llms nlp fine-tuning multimodal benchmarks safety

arXiv AI

Jun 2

Calibrating Uncertainty for Zero-Shot Adversarial CLIP

arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.

By Wenjing Lu, Zerui Tao, Yuning Qiu, Dongping Zhang, Yang Yang, Qibin Zhao

fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

Investigating Adversarial Robustness of Multi-modal Large Language Models

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

Calibrating Uncertainty for Zero-Shot Adversarial CLIP