Related papers: ceLLMate: Sandboxing Browser AI Agents
AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. With studies showing that up to 40% of AI-generated code…
Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost…
Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While…
Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…
Autonomous web agents solve complex browsing tasks, yet existing benchmarks measure only whether an agent finishes a task, ignoring whether it does so safely or in a way enterprises can trust. To integrate these agents into critical…
As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…
Web agents--autonomous systems that navigate and execute tasks on the web on behalf of users--have the potential to transform how people interact with the digital world. However, the most capable web agents today rely on proprietary models…
Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for…
While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for…
Large language models (LLMs) have shown strong capabilities in multi-step decision-making, planning and actions, and are increasingly integrated into various real-world applications. It is concerning whether their strong problem-solving…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In…
Graphical User Interface (GUI) agents powered by Large Vision-Language Models (LVLMs) have emerged as a revolutionary approach to automating human-machine interactions, capable of autonomously operating personal devices (e.g., mobile…
The increasing complexity and scale of modern digital environments have exposed significant gaps in traditional cybersecurity penetration testing methods, which are often time-consuming, labor-intensive, and unable to rapidly adapt to…
Leveraging users' behavioral data sampled by various sensors during the identification process, implicit authentication (IA) relieves users from explicit actions such as remembering and entering passwords. Various IA schemes have been…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting online human-agent interactions is slow and expensive, yet…
With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…
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…
Web-based activities span multiple webpages. However, conventional browsers with stacks of tabs cannot support operating and synthesizing large volumes of information across pages. While recent AI systems enable fully automated web browsing…