This paper provides a comprehensive, practitioner-oriented framework and survey to guide the selection and evaluation of differentially private methods for releasing sensitive graph data.

The paper proposes DAMPER, a domain-aware framework that autonomously extracts and rewrites private information from text while providing rigorous differential privacy guarantees, significantly improv…

The paper proposes an empirical calibration method, TeDA, to provide a more comparable and interpretable assessment of privacy loss for text rewriting mechanisms under Local Differential Privacy (LDP)…

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 proposes and evaluates DePRa, a system that democratizes privacy assessment by making everyday users active evaluators of mobile app data access, showing its potential to complement expert a…

This case study systematically measures how placing anonymization at different points (dataset vs. generated answer) within the RAG pipeline affects the privacy-utility trade-off, demonstrating that p…

PolicyGapper is an LLM-based tool that automatically detects inconsistencies and omissions between a mobile app's Google Play Data Safety Section and its official Privacy Policy, identifying thousands…

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 proposes PriSrv, a novel private service discovery protocol that enhances wireless communication security and privacy by enabling fine-grained, multi-layered matching and mutual authenticati…

The paper proposes TRIP-RAG, a dynamic anonymization framework that selectively anonymizes sensitive entities in knowledge bases used for RAG, significantly improving utility while maintaining strong…

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…

PrivScope is a novel on-device governor that enforces task-scoped disclosure, ensuring sensitive information is abstracted to the least revealing form before being sent to a cloud language model, sign…

The paper analyzed 25 popular mental health apps and found significant privacy gaps, revealing that most apps fail to disclose embedded trackers and dangerous permissions, undermining informed user co…

This paper introduces an attack, PRIVX, demonstrating that even differentially private (DP) Graph Neural Network (GNN) explanations leak enough structural information to allow an adversary to accurate…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.

This paper investigates the privacy risk of reconstructing Personally Identifiable Information (PII) from Large Language Models (LLMs) that have undergone Supervised Finetuning (SFT), proposing a nove…

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 study empirically analyzed 41 mobile gaming apps, finding that while device ID disclosures were relatively consistent, location and personal information disclosures showed significant mismatches…

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…