English
Related papers

Related papers: MIRAGE: Context-Aware Prompt Injection against Mob…

200 papers

While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…

Computation and Language · Computer Science 2025-03-26 Wenhao You , Bryan Hooi , Yiwei Wang , Youke Wang , Zong Ke , Ming-Hsuan Yang , Zi Huang , Yujun Cai

The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI…

Cryptography and Security · Computer Science 2026-03-25 Yutao Luo , Haotian Zhu , Shuchao Pang , Zhigang Lu , Tian Dong , Yongbin Zhou , Minhui Xue

Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on…

Cryptography and Security · Computer Science 2026-01-21 Tailun Chen , Yu He , Yan Wang , Shuo Shao , Haolun Zheng , Zhihao Liu , Jinfeng Li , Zhizhen Qin , Yuefeng Chen , Zhixuan Chu , Zhan Qin , Kui Ren

While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and usability in different applications. Recent years have seen growing interest in engaging…

Human-Computer Interaction · Computer Science 2025-04-01 Matheus Kunzler Maldaner , Wesley Hanwen Deng , Jason Hong , Ken Holstein , Motahhare Eslami

Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in dynamic on-device ecosystems, which include notifications, pop-ups, and inter-app interactions,…

Cryptography and Security · Computer Science 2026-03-06 Chiyu Chen , Xinhao Song , Yunkai Chai , Yang Yao , Haodong Zhao , Lijun Li , Jie Li , Yan Teng , Gongshen Liu , Yingchun Wang

Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remains underexplored. While agents are vulnerable to visual prompt injections, stealthily executing…

Cryptography and Security · Computer Science 2026-04-10 Renhua Ding , Xiao Yang , Zhengwei Fang , Jun Luo , Kun He , Jun Zhu

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

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…

Computation and Language · Computer Science 2025-09-25 Ziang Ye , Yang Zhang , Wentao Shi , Xiaoyu You , Fuli Feng , Tat-Seng Chua

Autonomous vehicles depend on online HD map construction to perceive lane boundaries, dividers, and pedestrian crossings -- safety-critical road elements that directly govern motion planning. While existing pixel perturbation attacks can…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Chenyi Wang , Ruoyu Song , Raymond Muller , Jean-Philippe Monteuuis , Jonathan Petit , Z. Berkay Celik , Ryan Gerdes , Ming F. Li

Instruction-guided image editing has seen remarkable progress with models like FLUX.2 and Qwen-Image-Edit, yet they still struggle with complex scenarios with multiple similar instances each requiring individual edits. We observe that…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Ziqian Liu , Stephan Alaniz

Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Jui-Cheng Chiu , Yu-Chao Wang , Shengyang Luo , Tongyan Wang , Qi Yang , Nabin Khanal , Yingjie Victor Chen

Large Language Models (LLMs) have shown remarkable capabilities in environmental perception, reasoning-based decision-making, and simulating complex human behaviors, particularly in interactive role-playing contexts. This paper introduces…

Computation and Language · Computer Science 2026-01-21 Yin Cai , Zhouhong Gu , Zhaohan Du , Zheyu Ye , Shaosheng Cao , Yiqian Xu , Hongwei Feng , Ping Chen

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended…

Cryptography and Security · Computer Science 2026-04-29 Mengyao Du , Han Fang , Haokai Ma , Jiahao Chen , Kai Xu , Quanjun Yin , Ee-Chien Chang

Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…

Cryptography and Security · Computer Science 2026-04-15 Guohong Liu , Jialei Ye , Jiacheng Liu , Yuanchun Li , Wei Liu , Pengzhi Gao , Jian Luan , Yunxin Liu

Multi-modal large language model (MLLM)-based web agents interact with webpage environments by generating actions based on screenshots of the webpages. In this work, we propose WebInject, a prompt injection attack that manipulates the…

Machine Learning · Computer Science 2025-10-20 Xilong Wang , John Bloch , Zedian Shao , Yuepeng Hu , Shuyan Zhou , Neil Zhenqiang Gong

Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output text, OS agents autonomously perform computer-based tasks in…

Cryptography and Security · Computer Science 2026-01-28 Lukas Aichberger , Alasdair Paren , Guohao Li , Philip Torr , Yarin Gal , Adel Bibi

Access to diverse, well-annotated medical images with interactive learning tools is fundamental for training practitioners in medicine and related fields to improve their diagnostic skills and understanding of anatomical structures. While…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Miguel Diaz Benito , Cecilia Diana Albelda , Alvaro Garcia Martin , Jesus Bescos Cano , Marcos Escudero-Vinolo , Juan C. SanMiguel

Traffic is inherently dangerous, with around 1.19 million fatalities annually. Automotive Mediated Reality (AMR) can enhance driving safety by overlaying critical information (e.g., outlines, icons, text) on key objects to improve…

Human-Computer Interaction · Computer Science 2026-01-28 Pascal Jansen , Julian Britten , Mark Colley , Markus Sasalovici , Enrico Rukzio

Graphical User Interface (GUI) agents are increasingly deployed to interact with online web services, yet their exposure to open-world content renders them vulnerable to Environmental Injection Attacks (EIAs). In these attacks, an attacker…

Cryptography and Security · Computer Science 2026-02-03 Yitong Zhang , Ximo Li , Liyi Cai , Jia Li

Attackers can exploit known vulnerabilities to infiltrate a device's firmware and the communication between firmware binaries, in order to pass between them. To improve cybersecurity, organizations must identify and mitigate the risks of…

Cryptography and Security · Computer Science 2023-11-08 David Tayouri , Telem Nachum , Asaf Shabtai
‹ Prev 1 2 3 10 Next ›