English
Related papers

Related papers: LLM-based Privacy Data Augmentation Guided by Know…

200 papers

Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels. Despite its rigorous privacy guarantee, it has been observed that in practice…

Machine Learning · Computer Science 2023-06-06 Ruihan Wu , Jin Peng Zhou , Kilian Q. Weinberger , Chuan Guo

Differential Privacy (DP) is a key property to protect data and models from integrity attacks. In the Deep Learning (DL) field, it is commonly implemented through the Differentially Private Stochastic Gradient Descent (DP-SGD). However,…

Machine Learning · Computer Science 2023-11-21 Jiménez-López , Daniel , Rodríguez-Barroso , Nuria , Luzón , M. Victoria , Herrera , Francisco

Local differential privacy (LDP) is a recently proposed privacy standard for collecting and analyzing data, which has been used, e.g., in the Chrome browser, iOS and macOS. In LDP, each user perturbs her information locally, and only sends…

Cryptography and Security · Computer Science 2019-07-02 Ning Wang , Xiaokui Xiao , Yin Yang , Jun Zhao , Siu Cheung Hui , Hyejin Shin , Junbum Shin , Ge Yu

User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy…

Machine Learning · Computer Science 2022-03-22 Anda Cheng , Peisong Wang , Xi Sheryl Zhang , Jian Cheng

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

Cryptography and Security · Computer Science 2021-05-18 Franziska Boenisch , Philip Sperl , Konstantin Böttinger

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

This work investigates the effectiveness of different pseudonymization techniques, ranging from rule-based substitutions to using pre-trained Large Language Models (LLMs), on a variety of datasets and models used for two widely used NLP…

Computation and Language · Computer Science 2023-06-12 Oleksandr Yermilov , Vipul Raheja , Artem Chernodub

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 $\textit{document-level}$ privatization. Recently,…

Computation and Language · Computer Science 2024-07-02 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

The task of text privatization using Differential Privacy has recently taken the form of $\textit{text rewriting}$, in which an input text is obfuscated via the use of generative (large) language models. While these methods have shown…

Computation and Language · Computer Science 2024-07-02 Stephen Meisenbacher , Maulik Chevli , Juraj Vladika , Florian Matthes

Estimating causal effects from randomized experiments is only possible if participants are willing to disclose their potentially sensitive responses. Differential privacy, a widely used framework for ensuring an algorithms privacy…

Machine Learning · Statistics 2025-05-29 Adel Javanmard , Vahab Mirrokni , Jean Pouget-Abadie

Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local…

Machine Learning · Computer Science 2020-05-19 Zonghao Huang , Rui Hu , Yuanxiong Guo , Eric Chan-Tin , Yanmin Gong

Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called "privacy amplification by subsampling" principle, which ensures that a differentially private…

Machine Learning · Computer Science 2018-11-26 Borja Balle , Gilles Barthe , Marco Gaboardi

The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. However, its application to large datasets containing personal information…

Machine Learning · Computer Science 2025-06-13 Julien Nicolas , César Sabater , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…

Machine Learning · Computer Science 2018-02-27 H. Brendan McMahan , Daniel Ramage , Kunal Talwar , Li Zhang

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…

Artificial Intelligence · Computer Science 2024-03-08 Tiejin Chen , Longchao Da , Huixue Zhou , Pingzhi Li , Kaixiong Zhou , Tianlong Chen , Hua Wei

While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (DNNs) for medical diagnostics. We propose Dopamine, a system…

Machine Learning · Computer Science 2021-02-01 Mohammad Malekzadeh , Burak Hasircioglu , Nitish Mital , Kunal Katarya , Mehmet Emre Ozfatura , Deniz Gündüz

Sensitive statistics are often collected across sets of users, with repeated collection of reports done over time. For example, trends in users' private preferences or software usage may be monitored via such reports. We study the…

Machine Learning · Computer Science 2020-07-28 Úlfar Erlingsson , Vitaly Feldman , Ilya Mironov , Ananth Raghunathan , Kunal Talwar , Abhradeep Thakurta

Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as…

Computation and Language · Computer Science 2025-03-21 Anmol Goel , Yaxi Hu , Iryna Gurevych , Amartya Sanyal

Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. Recent advancements in large language models (LLMs) have inspired a number of algorithm techniques for improving DP synthetic data…

Machine Learning · Computer Science 2025-02-11 Marika Swanberg , Ryan McKenna , Edo Roth , Albert Cheu , Peter Kairouz

We propose an ensemble learning framework with Poisson sub-sampling to effectively train a collection of teacher models to issue some differential privacy (DP) guarantee for training data. Through boosting under DP, a student model derived…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-13 Chao-Han Huck Yang , Jun Qi , Sabato Marco Siniscalchi , Chin-Hui Lee