arXiv Machine Learning

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

arXiv:2608. 08815v1 Announce Type: new Abstract: Traffic sign recognition (TSR) models based on deep neural networks achieve strong clean-data performance but remain vulnerable to physically realizable adversarial attacks, including shadow perturbations, natural-light interference, and printed patches.

arXiv AI

Jun 24

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).

By Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jul 28

Multi-model approach for autonomous driving: A comprehensive study on traffic sign-, vehicle- and lane detection and behavioral cloning

arXiv:2603. 09255v2 Announce Type: replace-cross Abstract: Deep learning and computer vision techniques have become increasingly important in the development of self-driving cars.

By Kanishkha Jaisankar, Pranav M. Pawar, Diana Susan Joseph, Raja Muthalagu, Mithun Mukherjee, Dnyaneshawar Mantri, Ramjee Prasad

agents computer-vision robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

arXiv AI

Aug 11

Multi-Task Consistency-based Detection of Adversarial Attacks

arXiv:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.

By Cong Chen, Jean-Philippe Monteuuis, Jonathan Petit

agents computer-vision robotics safety

arXiv AI

Jul 7

A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition

arXiv:2204. 02803v2 Announce Type: replace-cross Abstract: Sign language recognition from monocular video or 2D pose sequences is challenging, both because 3D information must be inferred from 2D observations and because the signal is inherently spatiotemporal.

By Silvan Ferreira, Esdras Costa, Marcio Dahia, Jampierre Rocha

llms rag

arXiv AI

Jul 14

Technical Report on the CVPR 2026@AdvML Workshop Challenge

arXiv:2607. 11560v1 Announce Type: cross Abstract: Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning.

By Tianyuan Zhang, Zonglei Jing, Jiangfan Liu, Ligong Zhang, Ke Ma, Chengzhi Sun, Xiaohai Xu, Zhirui Zhang, Qianqian Xu, Qingming Huang, Hanyu Fang, Junhua Liu, Zheng Wang, Xiaoliang Liu, Yuanbo Li, Shuai Gui, Bin Wang, Menghe Zheng, Jing Nie, Hanyang Meng, Zeyang Zhang, Xiang Zhang, Yongxuan Zhu, Rui Ding, Hainan Li, Yongkang Zhang, Zhilei Zhu, Xianglong Kong, Jin Hu, Zonghao Ying, Yisong Xiao, Lei Chen, Haotong Qin, Jiakai Wang, Aishan Liu, Ruikai Li, Julia Karbing, Yinpeng Dong, Zhenfei Yin, Shao Jing, Xia Hu, Jingyi Xu, Juntao Dai, Xinyun Chen, Vishal M. Patel, Xianglong Liu, Dawn Song, Alan Yuille, Philip H. S. Torr, Dacheng Tao

agents nlp multimodal benchmarks safety

arXiv Machine Learning

Aug 3

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations

arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.

By Jun Liu, Leo Yu Zhang, Fengpeng Li, Isao Echizen, Jiantao Zhou

computer-vision benchmarks safety

arXiv Machine Learning

Jul 2

Steal the Patch Size: Adversarially Manipulate Vision-Language Models

arXiv:2607. 00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline.

By Kai Hu, Akash Bharadwaj, Weichen Yu, Matt Fredrikson

llms nlp robotics multimodal safety

arXiv AI

Aug 10

TransSLR: A Lightweight Transformer for Sign Language Recognition

arXiv:2608. 06407v1 Announce Type: cross Abstract: Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem.

By Lucia Yen Wanchi, Samuel Johnny, Victor Tolulope Olufemi, Emmanuel Aaron, Moise Busogi

llms fine-tuning multimodal benchmarks

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

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 Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang

llms multimodal safety

Related stories