English
Related papers

Related papers: Large Language Models Can Be Strong Differentially…

200 papers

Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…

Cryptography and Security · Computer Science 2019-12-23 Lei Yu , Ling Liu , Calton Pu , Mehmet Emre Gursoy , Stacey Truex

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel…

Machine Learning · Computer Science 2020-10-06 Lingjuan Lyu , Xuanli He , Yitong Li

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious…

Machine Learning · Computer Science 2021-11-05 Da Yu , Huishuai Zhang , Wei Chen , Jian Yin , Tie-Yan Liu

Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…

Cryptography and Security · Computer Science 2024-10-04 Jessica Smith , David Williams , Emily Brown

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

In this work, we devise a parameter-efficient solution to bring differential privacy (DP) guarantees into adaptation of a cross-lingual speech classifier. We investigate a new frozen pre-trained adaptation framework for DP-preserving speech…

Sound · Computer Science 2023-08-28 Chun-Wei Ho , Chao-Han Huck Yang , Sabato Marco Siniscalchi

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Yu-Lin Tsai , Yizhe Li , Zekai Chen , Po-Yu Chen , Chia-Mu Yu , Xuebin Ren , Francois Buet-Golfouse

Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates can reduce utility on challenging datasets. We propose…

Machine Learning · Computer Science 2026-05-21 Mohammad Partohaghighi , Roummel Marcia

Federated learning (FL) allows clients to collaboratively train a global model without sharing their local data with a server. However, clients' contributions to the server can still leak sensitive information. Differential privacy (DP)…

Machine Learning · Computer Science 2025-02-18 Jie Xu , Karthikeyan Saravanan , Rogier van Dalen , Haaris Mehmood , David Tuckey , Mete Ozay

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly…

Cryptography and Security · Computer Science 2026-03-10 Meisam Mohammady , Qin Yang , Nicholas Stout , Ayesha Samreen , Han Wang , Christopher J Quinn , Yuan Hong

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Computers and Society · Computer Science 2019-12-03 Benjamin Clavié , Kobi Gal

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of Large Language Models. One solution consistently appearing in recent…

Computation and Language · Computer Science 2024-10-02 Stephen Meisenbacher , Florian Matthes

Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due to the need to capture complex structures under noisy…

Machine Learning · Computer Science 2025-04-30 Tejumade Afonja , Hui-Po Wang , Raouf Kerkouche , Mario Fritz

Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models for many downstream Natural Language Processing (NLP) tasks…

Machine Learning · Computer Science 2022-06-07 Fatemehsadat Mireshghallah , Arturs Backurs , Huseyin A Inan , Lukas Wutschitz , Janardhan Kulkarni

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model…

Machine Learning · Computer Science 2022-11-30 Jie Fu , Zhili Chen , Xiao Han

Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in…

Cryptography and Security · Computer Science 2025-02-21 Yanming Liu , Xinyue Peng , Yuwei Zhang , Xiaolan Ke , Songhang Deng , Jiannan Cao , Chen Ma , Mengchen Fu , Tianyu Du , Sheng Cheng , Xun Wang , Jianwei Yin , Xuhong Zhang

We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a $p$-dimensional space given $n$ i.i.d. samples drawn from a distribution. We improve…

Machine Learning · Computer Science 2020-08-12 Yingxue Zhou , Xiangyi Chen , Mingyi Hong , Zhiwei Steven Wu , Arindam Banerjee

Despite intense interest and considerable effort, the current generation of neural networks suffers a significant loss of accuracy under most practically relevant privacy training regimes. One particularly challenging class of neural…

Machine Learning · Computer Science 2021-06-07 Huanyu Zhang , Ilya Mironov , Meisam Hejazinia

This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of…

Cryptography and Security · Computer Science 2024-02-13 Pierre Tholoniat , Huseyin A. Inan , Janardhan Kulkarni , Robert Sim

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