Related papers: HackWorld: Evaluating Computer-Use Agents on Explo…
Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
Graphical user interface testing is significantly challenging, and automating it even more so. Test-driven development is impractical: it generally requires an initial implementation of the GUI to generate golden images or to construct…
Advancements in multimodal foundation models have enabled the development of Computer Use Agents (CUAs) capable of autonomously interacting with GUI environments. As CUAs are not restricted to certain tools, they allow to automate more…
Increasing number of cyber-attacks demotivate people to use Information and Communication Technology (ICT) for industrial as well as day to day work. A main reason for the increasing number of cyber-attacks is mistakes that programmers make…
Nowadays, user authentication is one of the important topics in information security. Text based strong password schemes could provide with certain degree of security. However, the fact that strong passwords being difficult to memorize…
Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…
This paper proposes a novel visual model for web applications security monitoring. Although an automated intrusion detection system can shield a web application from common attacks, it usually cannot detect more complicated break-ins. So, a…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in…
Modern web applications are dominated by HTTP/HTTPS messages that consist of one or more headers, where most of the exploits and payloads can be injected by attackers. According to the OWASP, the 80 percent of the web attacks are done…
The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs'…
Over the past three decades, computers have managed to make their way into a majority of households. Due to this enormous transition, the surge in the internets popularity was inevitable. Just like everything else, whatever has a pro also…
Computer Use Agents (CUAs) are designed to autonomously operate digital interfaces, yet they often fail to reliably determine whether a given task has been completed. We present an autonomous evaluation and feedback framework that uses…
Graphical User Interface (GUI) agents extend large language models from text generation to action execution in real-world digital environments. Unlike conversational systems, GUI agents perform irreversible operations such as submitting…
Large language model (LLM) agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored…
Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform complex tasks. This autonomy introduces serious security…
Modern overlay security mechanisms like Web Application Firewalls (WAF) suffer from inability to recognize custom high-level application logic and data objects, which results in low accuracy, high false positives rates, and overhelming…
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…
Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…