Related papers: MAGPIE: A benchmark for Multi-AGent contextual PrI…
LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and…
Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision support, the model…
As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user…
As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…
Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences. Calendar scheduling makes the trust problem concrete: an assistant must coordinate with other assistants while deciding what…
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…
The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and…
AI creates and exacerbates privacy risks, yet practitioners lack effective resources to identify and mitigate these risks. We present Privy, a tool that guides practitioners without privacy expertise through structured privacy impact…
Advanced AI assistants combine frontier LLMs and tool access to autonomously perform complex tasks on behalf of users. While the helpfulness of such assistants can increase dramatically with access to user information including emails and…
The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…
The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share more than necessary, increasing privacy risks via…
With the significant expansion of the context window in Large Language Models (LLMs), these models are theoretically capable of processing millions of tokens in a single pass. However, research indicates a significant gap between this…
Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant risk. To address the shortcomings of standard accuracy, this paper introduces a more…
Computer use agents create new privacy risks: training data collected from real websites inevitably contains sensitive information, and cloud-hosted inference exposes user screenshots. Detecting personally identifiable information in web…
Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination…
Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…
Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…
Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…
The recent swift development of LLMs like GPT-4, Gemini, and GPT-3.5 offers a transformative opportunity in medicine and healthcare, especially in digital diagnostics. This study evaluates each model diagnostic abilities by interpreting a…
The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…