相关论文: Privacy Practices of Browser Agents

Ensuring privacy of users of social networks is probably an unsolvable conundrum. At the same time, an informed use of the existing privacy options by the social network participants may alleviate - or even prevent - some of the more…

Large language models (LLMs) are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast…

Autonomous agents based on large language models (LLMs) are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper…

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Large language model (LLM) services have been rapidly integrated into people's daily lives as chatbots and agentic systems. They are nourished by collecting rich streams of data, raising privacy concerns around excessive collection of…

In the study of Human-Computer Interaction, privacy is often seen as a core issue, and it has been explored directly in connection with User Interface (UI) and User Experience (UX) design. We systematically investigate the key…

The current "notice and consent" paradigm is broken: consent dialogues are often manipulative, and users cannot realistically read or understand every privacy policy. While recent LLM-based tools empower users seeking active control, many…

Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications…

A fundamental tension exists between the demand for sophisticated AI assistance in web search and the need for user data privacy. Current centralized models require users to transmit sensitive browsing data to external services, which…

Third-party tracking is common on almost all commercially operated websites. Prior work has studied in detail the extent of third-party tracking on the web, detection of third-party trackers, and defending against third-party tracking.…

Voice assistant applications have become omniscient nowadays. Two models that provide the two most important functions for real-life applications (i.e., Google Home, Amazon Alexa, Siri, etc.) are Automatic Speech Recognition (ASR) models…

We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete…

This paper presents a novel application of large language models (LLMs) to enhance user comprehension of privacy policies through an interactive dialogue agent. We demonstrate that LLMs significantly outperform traditional models in tasks…

Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular…

In this work we present the first holistic survey of the agentic security landscape, structuring the field around three fundamental pillars: Applications, Threats, and Defenses. We provide a comprehensive taxonomy of over 160 papers,…

Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as…

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…

We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents. However, the dynamics of multi-agent collaboration under privacy constraints remain…