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