Related papers: Privacy Practices of Browser Agents
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.…
Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g.,…
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…
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…
Modern web browsers have effectively become the new operating system for business applications, yet their security posture is often under-scrutinized. This paper presents a novel, comprehensive Browser Security Posture Analysis…
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…
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…
Large language models (LLMs) are increasingly being integrated into web browsers to create agentic browsing systems that execute actions on behalf of the user. Prior work considering the security of agentic browsers focuses exclusively on…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
Web browsers are integral parts of everyone's daily life. They are commonly used for security-critical and privacy sensitive tasks, like banking transactions and checking medical records. Unfortunately, modern web browsers are too complex…
AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…
We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not…
To protect users' privacy, legislators have regulated the usage of tracking technologies, mandating the acquisition of users' consent before collecting data. Consequently, websites started showing more and more consent management modules --…
This article provides a quantitative analysis of privacy-compromising mechanisms on 1 million popular websites. Findings indicate that nearly 9 in 10 websites leak user data to parties of which the user is likely unaware; more than 6 in 10…
The paper analyses current versions of top three used Internet browsers and compare their security levels to a research done in 2006. The security is measured by analyzing how user data is stored. Data recorded during different browsing…
Nowadays, all major web browsers have a private browsing mode. However, the mode's benefits and limitations are not particularly understood. Through the use of survey studies, prior work has found that most users are either unaware of…
With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…
Websites are capable of learning a wide range of information about the platform on which a browser is executing. One major source of such information is the set of standardised Application Programming Interfaces (APIs) provided within the…
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…