The paper introduces PrivacySIM, an evaluation suite that benchmarks how well LLMs can simulate individual user privacy decisions based on persona attributes, finding that while conditioning improves…

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

This study quantifies the privacy risk of inferring sensitive personality traits from user interactions with LLM-based conversational agents, demonstrating that machine learning models can accurately…

This paper demonstrates that encrypted traffic metadata (packet lengths and timing) can leak a user's persona, achieving high inference accuracy across multiple modern websites.

The paper proposes Trajectory Induced Preference Optimization (TIPO) to improve mobile GUI agent personalization by explicitly modeling and optimizing for privacy-related behavioral differences in exe…

The paper evaluates LLM-based simulators for generating differentially private synthetic data, finding that while they show promise for utility, they suffer from significant distribution drift due to…

This study proposes a negotiation framework, using composite indices (RBTI and CATI), to explain how youth navigate competing privacy pressures when using smart voice assistants, finding that high usa…

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper proposes Information Sufficiency (IS) as a comprehensive framework for privacy-preserving LLM communication, demonstrating that free-text pseudonymization outperforms existing suppression an…

RealityTest introduces a large-scale, multimodal, and multilingual benchmark using real-world human data to test how AI systems disclose their identity, finding that context and phrasing are more crit…

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…

The paper introduces ImmersedPrivacy, an interactive audio-visual framework, and finds that current Vision-Language Models (VLMs) deployed in physical environments suffer from significant deficits in…

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

The paper introduces an adaptive interview framework to gather rich persona context, demonstrating that LLMs improve decision alignment in moral dilemmas only when they selectively ground their decisi…

The paper introduces ChildEval, a large-scale benchmark designed to systematically evaluate how well large language models can infer and follow complex, child-specific preferences during long-context…

This study investigates user perceptions of privacy risks associated with GenAI smartphones, finding that users express heightened concerns across the entire data lifecycle and suggest comprehensive,…

This study investigated user reactions to inferred personal information from their own ChatGPT histories, finding that acceptability is governed by context-sensitive norms regarding generation, retent…

The paper investigates how users perceive and utilize security and privacy transparency in consumer-facing generative AI, finding that users rely on proxies like popularity and require actionable, tru…

The paper introduces EUDAIMONIA, a new framework and benchmark for evaluating how well LLMs align with user welfare in social interactions, finding that even state-of-the-art models frequently violate…

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current…