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 proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels…

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…

MaskClaw is an edge-side privacy arbitrator that protects sensitive data in GUI agent screenshots by combining local visual evidence, task-specific policies, and a skill-evolution mechanism.

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 introduces Narriva, a method that generates text-based synthetic privacy personas grounded in past user behavior to accurately and efficiently simulate individual and population-level privac…

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 introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby supp…

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

The paper proposes FedVPA-GP, a federated learning framework that uses a Gumbel-Softmax prior and orthogonal loss to personalize LLM alignment by disentangling conflicting user preferences while maint…

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

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…

This study empirically demonstrates that privacy exposure in mobile gaming apps is primarily driven by complex, configuration-level SDK ecosystems rather than just the permissions the app explicitly r…

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…

The paper proposes SELFCI, a complementary self-distillation framework that effectively balances the privacy requirements of Contextual Integrity (CI) with the utility of large language models, outper…

WebTrap introduces a stealthy, mid-task hijacking attack that successfully compromises browser agents during long-horizon tasks by seamlessly fusing malicious instructions with the original user goal.

The paper introduces WebPII, a novel, large-scale synthetic benchmark for detecting personally identifiable information (PII) in web screenshots, and demonstrates a model (WebRedact) that significantl…

This paper introduces personalized empathy, a capability for LLMs to adapt empathetic strategies based on individual user history, and proposes PereGRM, a reward modeling framework that significantly…