Related papers: MirrorGuard: Toward Secure Computer-Use Agents via…

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic…

Since the first Graphical User Interface (GUI) prototype was invented in the 1970s, GUI systems have been deployed into various personal computer systems and server platforms. Recently, with the development of artificial intelligence (AI)…

Security risk assessment is essential in establishing the trustworthiness and reliability of modern systems. While various security risk assessment approaches exist, prevalent applications are "pen and paper" implementations that -- even if…

The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to…

With the widespread application of large language models in code generation, recent studies demonstrate that employing additional Chain-of-Thought generation models can significantly enhance code generation performance by providing explicit…

The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by…

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

Patient safety training is essential for preparing healthcare professionals to identify, investigate, and prevent adverse events. However, conventional simulation-based approaches often require substantial faculty time, physical resources,…

Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…

Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

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…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain…

While the digitization of industrial factories provides tremendous improvements for the production of goods, it also renders such systems vulnerable to serious cyber-attacks. To research, test, and validate security measures protecting…

System prompts for AI coding agents increasingly employ motivational framing -- from neutral task descriptions to fear-driven threats -- yet no controlled study has examined whether such framing affects agent behavior. We present two…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to…