arXiv Machine Learning June 9, 2026 By Ji Guo, Wenbo Jiang, Yansong Lin, Yijing Liu, Ruichen Zhang, Guomin Lu, Aiguo Chen, Xinshuo Han, Hongwei Li

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space

Read the original on arXiv Machine Learning →

arXiv:2601. 04266v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

arXiv:2601. 14323v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored.

By Bingxin Xu, Yuzhang Shang, Binghui Wang, Emilio Ferrara

rag robotics multimodal safety

arXiv Machine Learning

Jun 3

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks

arXiv:2606. 02947v1 Announce Type: new Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks.

By Ivan Saboli\'c, Marin Or\v{s}i\'c, Josip \v{S}ari\'c, Sven Lon\v{c}ari\'c

llms fine-tuning multimodal

arXiv AI

Jun 10

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

arXiv:2407. 20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities.

By Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Changgan Yin, Minghui Li, Lulu Xue, Yichen Wang, Shengshan Hu, Aishan Liu, Peijin Guo, Leo Yu Zhang

llms agents robotics benchmarks safety

arXiv AI

Aug 12

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

arXiv:2608. 10393v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks.

By Jiahui Han, Yuhui Yao, Xin Wang, Jiafei Cao, Mingxuan Zhang, Danfeng Shan, Huiqi Deng, Guanchu Wang, Xia Hu

diffusion robotics multimodal safety

arXiv Machine Learning

6d ago

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.

By Yiyang Zhang, Chaojian Yu, Ziming Hong, Yuanjie Shao, Qinmu Peng, Tongliang Liu, Xinge You

nlp multimodal safety

arXiv AI

Jul 7

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models

arXiv:2508. 08521v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront.

By Mansi Phute, Ravikumar Balakrishnan

llms robotics multimodal benchmarks safety

Related stories

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models