Related papers: AgentRAE: Remote Action Execution through Notifica…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Recent advances in vision-language models (VLMs) and reinforcement learning (RL) have driven progress in GUI automation. However, most existing methods rely on static, one-shot visual inputs and passive perception, lacking the ability to…

Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph…

In this paper, we show that when the communication between GenAI-powered applications relies on RAG-based inference, an attacker can initiate a computer worm-like chain reaction that we call Morris-II. This is done by crafting an…

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack…

Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve…

Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt injection, indirect instructions, and visual attacks. Existing defenses typically rely on…

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…

Due to the importance of Android app quality assurance, many automated GUI testing tools have been developed. Although the test algorithms have been improved, the impact of GUI rendering has been overlooked. On the one hand, setting a long…

The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information (PII) are often sent to untrusted, third-party routers.…

Web-use agents are rapidly being deployed to automate complex web tasks with extensive browser capabilities. However, these capabilities create a critical and previously unexplored attack surface. This paper demonstrates how attackers can…

Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt…

With the advancement of Multimodal Large Language Models (MLLM), LLM-driven visual agents are increasingly impacting software interfaces, particularly those with graphical user interfaces. This work introduces a novel LLM-based multimodal…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…