Related papers: AgentRAE: Remote Action Execution through Notifica…

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we…

Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility…

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…

Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end…

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. Though prior work has explored backdoor attacks against diffusion models for image or unconditional graph generation,…

Mobile GUI agents have shown strong potential in real-world automation and practical applications. However, most existing agents remain reactive, making decisions mainly from current screen, which limits their performance on long-horizon…

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion…

Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the…

As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer, dynamically synthesizing the right controls, options, and…

Graphical User Interface (GUI) Agents, powered by large language and vision-language models, hold promise for enabling end-to-end automation in digital environments. However, their progress is fundamentally constrained by the scarcity of…

Developing and testing user interfaces (UIs) and training AI agents to interact with them are challenging due to the dynamic and diverse nature of real-world mobile environments. Existing methods often rely on cumbersome physical devices or…

Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops, where agents cycle through the same failing actions without recovery. We…

Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these…

Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in simulation and often…

Graphical User Interface (GUI) agents possess significant commercial and social value, and GUI agents powered by advanced multimodal large language models (MLLMs) have demonstrated remarkable potential. Currently, existing GUI agents…

In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Most existing guardrails for CUAs adopt a reactive approach,…