Related papers: HackWorld: Evaluating Computer-Use Agents on Explo…
Large language models (LLMs) are increasingly being used in Metaverse environments to generate dynamic and realistic content and to control the behavior of non-player characters (NPCs). However, the cybersecurity concerns associated with…
Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use…
Computer-use agents (CUAs) hold the promise of performing a wide variety of general tasks, but current evaluations have primarily focused on simple scenarios. It therefore remains unclear whether such generalist agents can automate more…
In the ever-evolving discipline of high-dimensional scientific data, collaborative immersive analytics (CIA) offers a promising frontier for domain experts in complex data visualization and interpretation. This research presents a…
This article puts forward the use of mutual information values to replicate the expertise of security professionals in selecting features for detecting web attacks. The goal is to enhance the effectiveness of web application firewalls…
Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual…
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…
Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or vision language models operating on page screenshots. However, web pages often change between…
Web services are becoming business-critical components, often deployed with critical software bugs that can be maliciously explored. Web vulnerability scanners allow the detection of security vulnerabilities in web services by stressing the…
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…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
Quantum computing is a cutting-edge field of information technology that harnesses the principles of quantum mechanics to perform computations. It has major implications for the cyber security industry. Existing cyber protection…
Web traffic has evolved to include both human users and automated agents, ranging from benign web crawlers to adversarial scanners such as those capable of credential stuffing, command injection, and account hijacking at the web scale. The…
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…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
Mobile devices rely on Trusted Execution Environments (TEEs) to execute security-critical code and protect sensitive assets. This security-critical code is modularized in components known as Trusted Applications (TAs). Vulnerabilities in…
The prospect of artificial intelligence (AI) competing in the adversarial landscape of cyber security has long been considered one of the most impactful, challenging, and potentially dangerous applications of AI. Here, we demonstrate a new…
Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…
The use of passwords and the need to protect passwords are not going away. The majority of websites that require authentication continue to support password authentication. Even high-security applications such as Internet Banking portals,…
AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…