相关论文: Code Agent can be an End-to-end System Hacker: Ben…

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Code large language models (CodeLLMs) and agents are increasingly being integrated into complex software engineering tasks spanning the entire Software Development Life Cycle (SDLC). Benchmarking is critical for rigorously evaluating these…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

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…

The quality of datasets plays an increasingly crucial role in the research and development of modern artificial intelligence (AI). Despite the proliferation of open dataset platforms nowadays, data quality issues, such as incomplete…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, large language models (LLMs) with strong common sense knowledge have emerged in the domain of ITD. Nevertheless, diverse activity…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…

The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional techniques, while cornerstone for software quality…

Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with…

Computer Use Agents (CUAs) operate interfaces by pointing, clicking, and typing -- mirroring interactions of sighted users (SUs) who can thus monitor CUAs and share control. CUAs do not reflect interactions by blind and low-vision users…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Software robots have long been used in Robotic Process Automation (RPA) to automate mundane and repetitive computer tasks. With the advent of Large Language Models (LLMs) and their advanced reasoning capabilities, these agents are now able…

Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Blind Goal-Directedness (BGD): a bias to pursue goals…

The proliferation of Large Language Model (LLM)-based Graphical User Interface (GUI) agents in web browsing scenarios present complex unintended consequences (UCs). This paper characterizes three UCs from three perspectives: phenomena,…

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…

Large Language Model (LLM)-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks (e.g., prompt…

CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat intelligence (CTI) and develop detection rules. The benchmark provides a realistic…

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…