Related papers: Preference Redirection via Attention Concentration…
Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…
Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce new attack surfaces for adversarial manipulation that exploit…
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…
Adversarial examples have revealed the vulnerability of deep learning models and raised serious concerns about information security. The transfer-based attack is a hot topic in black-box attacks that are practical to real-world scenarios…
Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can…
Vision-language model (VLM)-based web agents increasingly power high-stakes selection tasks like content recommendation or product ranking by combining multimodal perception with preference reasoning. Recent studies reveal that these agents…
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of…
Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of large vision-language models (VLMs). However, these agents…
Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…
Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…
Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…
AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…
LLM-powered computer-use agents (CUAs) are shifting users from direct manipulation to supervisory coordination. Existing oversight mechanisms, however, have largely been studied as isolated interface features, making broader oversight…
Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…
Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…
Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…
As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark…
The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…
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)…