PrivacyAssist is a multi-agent LLM framework that detects inconsistencies between user-granted app permissions and the app's actual data collection practices, finding that most apps are not fully tran…

This study empirically analyzed 1,000 Android apps, finding that privacy policies are often vague and frequently fail to align with the actual sensitive data logged by the applications.

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to demonstrate that unnecessary acquisition of sensitive data is a widespread and critical priva…

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to show that unnecessary and sensitive data acquisition is a widespread and critical privacy vul…

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly impro…

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

The study surveyed Android developers to assess their willingness to adopt changes that mitigate device fingerprinting risks, finding that developers overwhelmingly support privacy protections even wi…

The paper introduces GAAP, an execution environment that deterministically guarantees the confidentiality of private user data by enforcing user-defined permission specifications on AI agents, even ag…

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.

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…

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 a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while…

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

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 introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

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…

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization,…

The paper analyzes Android's permission system and finds that two legacy mechanisms—permission groups and normal-level custom permissions—allow apps to silently gain excessive permissions and expose s…

The paper empirically compares the security and privacy implementation characteristics of major Android messaging apps (Meta Messenger, Signal, and Telegram) using static and dynamic analysis, finding…