中文
相关论文

相关论文: GhostEI-Bench: Do Mobile Agents Resilience to Envi…

200 篇论文

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

计算与语言 · 计算机科学 2025-05-26 Pengzhou Cheng , Haowen Hu , Zheng Wu , Zongru Wu , Tianjie Ju , Zhuosheng Zhang , Gongshen Liu

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…

密码学与安全 · 计算机科学 2026-04-10 Wenkui Yang , Chao Jin , Haisu Zhu , Weilin Luo , Derek Yuen , Kun Shao , Huaibo Huang , Junxian Duan , Jie Cao , Ran He

Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online…

人机交互 · 计算机科学 2026-04-09 Yichen Gong , Zhuohan Cai , Sunhao Dai , Yuqi Zhou , Zhangxuan Gu , Changhua Meng , Shuheng Shen

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI)…

计算与语言 · 计算机科学 2024-08-06 Qiusi Zhan , Zhixiang Liang , Zifan Ying , Daniel Kang

VLM-based mobile agents are increasingly popular due to their capabilities to interact with smartphone GUIs and XML-structured texts and to complete daily tasks. However, existing online benchmarks struggle with obtaining stable reward…

计算与语言 · 计算机科学 2026-02-03 Weikai Xu , Zhizheng Jiang , Yuxuan Liu , Pengzhi Gao , Wei Liu , Jian Luan , Yuanchun Li , Yunxin Liu , Bin Wang , Bo An

Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental…

人工智能 · 计算机科学 2026-05-14 Youngmin Im , Byeongung Jo , Jaeyoung Wi , Seungwoo Baek , Tae Hoon Min , Joo Hyung Lee , Sangeun Oh , Insik Shin , Sunjae Lee

The adoption of Vision-Language Models (VLMs) in embodied AI agents, while being effective, brings safety concerns such as jailbreaking. Prior work have explored the possibility of directly jailbreaking the embodied agents through…

密码学与安全 · 计算机科学 2025-11-21 Chunyang Li , Zifeng Kang , Junwei Zhang , Zhuo Ma , Anda Cheng , Xinghua Li , Jianfeng Ma

AI agents integrated with Web3 offer autonomy and openness but raise security concerns as they interact with financial protocols and immutable smart contracts. This paper investigates the vulnerabilities of AI agents within blockchain-based…

密码学与安全 · 计算机科学 2025-07-10 Atharv Singh Patlan , Peiyao Sheng , S. Ashwin Hebbar , Prateek Mittal , Pramod Viswanath

Training Vision-Language Models (VLMs) for Graphical User Interfaces (GUI) agents via Reinforcement Learning (RL) faces critical challenges: environment-based RL requires costly interactions, while environment-free methods struggle with…

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…

人工智能 · 计算机科学 2026-05-13 Strick Sheng , Ziyue Wang , Liyi Zhou

This paper investigates the faithfulness of multimodal large language model (MLLM) agents in a graphical user interface (GUI) environment, aiming to address the research question of whether multimodal GUI agents can be distracted by…

计算与语言 · 计算机科学 2025-09-08 Xinbei Ma , Yiting Wang , Yao Yao , Tongxin Yuan , Aston Zhang , Zhuosheng Zhang , Hai Zhao

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

密码学与安全 · 计算机科学 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However, the current fully autonomous paradigm poses potential safety…

人工智能 · 计算机科学 2026-04-28 Qihang Ai , Pi Bu , Yue Cao , Yingyao Wang , Jihao Gu , Jingxuan Xing , Zekun Zhu , Wei Jiang , Zhicheng Zheng , Jun Song , Yuning Jiang

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Jiamin Chang , Minhui Xue , Ruoxi Sun , Shuchao Pang , Salil S. Kanhere , Hammond Pearce

As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are embedded into the…

人工智能 · 计算机科学 2025-05-21 Yijie Lu , Tianjie Ju , Manman Zhao , Xinbei Ma , Yuan Guo , ZhuoSheng Zhang

Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

密码学与安全 · 计算机科学 2025-11-07 Chenghao Du , Quanfeng Huang , Tingxuan Tang , Zihao Wang , Adwait Nadkarni , Yue Xiao

As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments becomes critical. Unlike digital chatbots, these agents operate in…

密码学与安全 · 计算机科学 2026-05-11 Junran Wang , Xinjie Shen , Zehao Jin , Pan Li

The assurance of mobile app GUI has become increasingly important, as the GUI serves as the primary medium of interaction between users and apps. Although numerous automated GUI testing approaches have been developed with diverse…

软件工程 · 计算机科学 2026-05-05 Shengcheng Yu , Yuchen Ling , Chunrong Fang , Quan Zhou , Yi Zhao , Chunyang Chen , Shaomin Zhu , Zhenyu Chen

As large language models (LLMs) continue to improve in reasoning and decision-making, there is a growing need for realistic and interactive environments where their abilities can be rigorously evaluated. We present VirtualEnv, a…

人工智能 · 计算机科学 2026-02-10 Kabir Swain , Sijie Han , Ayush Raina , Jin Zhang , Shuang Li , Michael Stopa , Antonio Torralba