English
Related papers

Related papers: Selective Pre-training for Private Fine-tuning

200 papers

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Machine Learning · Computer Science 2024-11-26 Olivia Ma , Jonathan Passerat-Palmbach , Dmitrii Usynin

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

Machine Learning · Statistics 2018-12-21 Martín Abadi , Andy Chu , Ian Goodfellow , H. Brendan McMahan , Ilya Mironov , Kunal Talwar , Li Zhang

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Machine Learning · Statistics 2022-02-15 Hannah Brown , Katherine Lee , Fatemehsadat Mireshghallah , Reza Shokri , Florian Tramèr

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Machine Learning · Computer Science 2025-11-20 Bishnu Bhusal , Manoj Acharya , Ramneet Kaur , Colin Samplawski , Anirban Roy , Adam D. Cobb , Rohit Chadha , Susmit Jha

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Computation and Language · Computer Science 2023-02-17 Tong Guo

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

Machine Learning · Computer Science 2024-01-12 Alexey Kurakin , Natalia Ponomareva , Umar Syed , Liam MacDermed , Andreas Terzis

This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models by proposing a parameter-efficient method that integrates differential privacy noise allocation with gradient…

Computation and Language · Computer Science 2025-12-09 Yulin Huang , Yaxuan Luan , Jinxu Guo , Xiangchen Song , Yuchen Liu

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models…

Cryptography and Security · Computer Science 2023-05-02 Rouzbeh Behnia , Mohamamdreza Ebrahimi , Jason Pacheco , Balaji Padmanabhan

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

Cryptography and Security · Computer Science 2024-09-24 Nico Manzonelli , Wanrong Zhang , Salil Vadhan

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…

Machine Learning · Computer Science 2020-06-17 Neel Patel , Reza Shokri , Yair Zick

Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy…

Machine Learning · Statistics 2018-12-10 Koen Lennart van der Veen , Ruben Seggers , Peter Bloem , Giorgio Patrini

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…

Differential Privacy (DP) can be applied to raw text by exploiting the spatial arrangement of words in an embedding space. We investigate the implications of such text privatization on Language Models (LMs) and their tendency towards…

Computation and Language · Computer Science 2024-07-02 Stefan Arnold , Rene Gröbner , Annika Schreiner

Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving…

Machine Learning · Computer Science 2018-05-10 Cynthia Dwork , Vitaly Feldman

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

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

Machine Learning · Computer Science 2021-09-07 Ashly Lau , Jonathan Passerat-Palmbach

Economics and social science research often require analyzing datasets of sensitive personal information at fine granularity, with models fit to small subsets of the data. Unfortunately, such fine-grained analysis can easily reveal…

Machine Learning · Computer Science 2020-07-13 Daniel Alabi , Audra McMillan , Jayshree Sarathy , Adam Smith , Salil Vadhan

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…

Machine Learning · Statistics 2019-10-04 Zhengli Zhao , Nicolas Papernot , Sameer Singh , Neoklis Polyzotis , Augustus Odena

Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the…

Machine Learning · Computer Science 2024-02-13 Mohammad Hoseinpour , Milad Hoseinpour , Ali Aghagolzadeh