Related papers: Privacy Practices of Browser Agents
Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…
We present a study of how local frames (i.e., iframes loading content like "about:blank") are mishandled by a wide range of popular Web security and privacy tools. As a result, users of these tools remain vulnerable to the very attack…
With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as…
Modern web browsers are incredibly complex, with millions of lines of code and over one thousand JavaScript functions and properties available to website authors. This work investigates how these browser features are used on the modern,…
Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…
Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Harm to the privacy of users through data leakage is not an unknown issue, however, it has not been studied in the context of the crash reporting system. Automatic Crash Reporting Systems (ACRS) are used by applications to report…
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers…
While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we…
Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security…
A variety of tools have been introduced recently that are designed to help people protect their privacy on the Internet. These tools perform many different functions in-cluding encrypting and/or anonymizing communications, preventing the…
Virtual assistants (VAs) have seen increased use in recent years due to their ease of use for daily tasks. Despite their growing prevalence, their security and privacy implications are still not well understood. To address this gap, we…
Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user…
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…
Smartphones bring significant convenience to users but also enable devices to extensively record various types of personal information. Existing smartphone agents powered by Multimodal Large Language Models (MLLMs) have achieved remarkable…
A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs). These attacks may extract private information or coerce the model into producing harmful outputs. In real-world deployments,…
The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model of privacy management, rooted in a user's unilateral…