paper-with-me

홈 › Papers

VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation

2025-07-09 · Ziang Ye, Yang Zhang, Wentao Shi, Xiaoyu You, Fuli Feng, Tat-Seng Chua

Graphical User Interface (GUI) agents powered by Large Vision-Language Models (LVLMs) have emerged as a revolutionary approach to automating human-machine interactions, capable of autonomously operating personal devices (e.g., mobile phones) or applications within the device to perform complex real-world tasks in a human-like manner. However, their close integration with personal devices raises significant security concerns, with many threats, including backdoor attacks, remaining largely unexplored. This work reveals that the visual grounding of GUI agent-mapping textual plans to GUI elements-can introduce vulnerabilities, enabling new types of backdoor attacks. With backdoor attack targeting visual grounding, the agent's behavior can be compromised even when given correct task-solving plans. To validate this vulnerability, we propose VisualTrap, a method that can hijack the grounding by misleading the agent to locate textual plans to trigger locations instead of the intended targets. VisualTrap uses the common method of injecting poisoned data for attacks, and does so during the pre-training of visual grounding to ensure practical feasibility of attacking. Empirical results show that VisualTrap can effectively hijack visual grounding with as little as 5% poisoned data and highly stealthy visual triggers (invisible to the human eye); and the attack can be generalized to downstream tasks, even after clean fine-tuning. Moreover, the injected trigger can remain effective across different GUI environments, e.g., being trained on mobile/web and generalizing to desktop environments. These findings underscore the urgent need for further research on backdoor attack risks in GUI agents.

📄 PDF Abstract BibTeX arXiv:2507.06899

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackVisual Grounding

Similar Papers 제목 키워드 기반

Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing

2022-01-09 · Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…

Backdoor AttackText Classification

A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning

2024-09-12 · Yinbo Yu, Saihao Yan, Jiajia Liu

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform abnormal actions leading to failu…

Backdoor AttackDeep Reinforcement LearningSMACSMAC+

Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features

2024-12-10 · Xiaoyang Ning, Qing Xie, Jinyu Xu, Wenbo Jiang 외

Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the exis…

Backdoor AttackBayesian Optimization

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

2023-07-17 · Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao 외

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where…

Backdoor Attackspeech-recognitionSpeech Recognition

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers

2026-04-21 · Dazhuang Liu, Yanqi Qiao, Rui Wang, Kaitai Liang 외 arxiv

Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger loc…