A survey on differential privacy for unstructured data content

Y Zhao, J Chen - ACM Computing Surveys (CSUR), 2022‏ - dl.acm.org
Huge amounts of unstructured data including image, video, audio, and text are ubiquitously
generated and shared, and it is a challenge to protect sensitive personal information in …

Differentially private natural language models: Recent advances and future directions

L Hu, I Habernal, L Shen, D Wang - arxiv preprint arxiv:2301.09112, 2023‏ - arxiv.org
Recent developments in deep learning have led to great success in various natural
language processing (NLP) tasks. However, these applications may involve data that …

Synthetic text generation with differential privacy: A simple and practical recipe

X Yue, HA Inan, X Li, G Kumar, J McAnallen… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Privacy concerns have attracted increasing attention in data-driven products due to the
tendency of machine learning models to memorize sensitive training data. Generating …

Sentence-level privacy for document embeddings

C Meehan, K Mrini, K Chaudhuri - arxiv preprint arxiv:2205.04605, 2022‏ - arxiv.org
User language data can contain highly sensitive personal content. As such, it is imperative
to offer users a strong and interpretable privacy guarantee when learning from their data. In …

Scenario-based Adaptations of Differential Privacy: A Technical Survey

Y Zhao, JT Du, J Chen - ACM Computing Surveys, 2024‏ - dl.acm.org
Differential privacy has been a de facto privacy standard in defining privacy and handling
privacy preservation. It has had great success in scenarios of local data privacy and …

Privacy-preserving data integration and sharing in multi-party iot environments: An entity embedding perspective

J Lu, H Leung, N **e - Information Fusion, 2024‏ - Elsevier
The increasing prevalence of IoT applications highlights the urgency for insightful data
fusion and information acquisition, boosting data integration and sharing needs. However …

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy

S Meisenbacher, M Chevli, F Matthes - arxiv preprint arxiv:2405.01678, 2024‏ - arxiv.org
The study of privacy-preserving Natural Language Processing (NLP) has gained rising
attention in recent years. One promising avenue studies the integration of Differential …

Just rewrite it again: A post-processing method for enhanced semantic similarity and privacy preservation of differentially private rewritten text

S Meisenbacher, F Matthes - … of the 19th International Conference on …, 2024‏ - dl.acm.org
The study of Differential Privacy (DP) in Natural Language Processing often views the task of
text privatization as a rewriting task, in which sensitive input texts are rewritten to hide …

Private Language Models via Truncated Laplacian Mechanism

T Huang, T Yang, I Habernal, L Hu, D Wang - arxiv preprint arxiv …, 2024‏ - arxiv.org
Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent
privacy leakage, researchers have investigated word-level perturbations, relying on the …

A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy

S Meisenbacher, M Chevli, F Matthes - arxiv preprint arxiv:2407.00638, 2024‏ - arxiv.org
Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level
on which a proposed mechanism operates, often taking the form of $\textit {word-level} $ or …