English
Related papers

Related papers: Public Data Assisted Differentially Private In-Con…

200 papers

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs…

Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive, there is a key challenge in designing privacy-preserving…

Cryptography and Security · Computer Science 2022-04-05 Héber H. Arcolezi

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

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

We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when…

Machine Learning · Computer Science 2024-04-16 Boxin Wang , Yibo Jacky Zhang , Yuan Cao , Bo Li , H. Brendan McMahan , Sewoong Oh , Zheng Xu , Manzil Zaheer

In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…

Computation and Language · Computer Science 2025-03-21 Mario Sanz-Guerrero , Katharina von der Wense

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

Cryptography and Security · Computer Science 2021-12-06 Honglu Jiang , Yifeng Gao , S M Sarwar , Luis GarzaPerez , Mahmudul Robin

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…

Machine Learning · Computer Science 2023-06-29 Tyler LeBlond , Joseph Munoz , Fred Lu , Maya Fuchs , Elliott Zaresky-Williams , Edward Raff , Brian Testa

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not…

Cryptography and Security · Computer Science 2023-01-09 Alberto Blanco-Justicia , David Sanchez , Josep Domingo-Ferrer , Krishnamurty Muralidhar

Large Language Models (LLMs) have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about…

Cryptography and Security · Computer Science 2025-05-16 Haoqi Wu , Wei Dai , Li Wang , Qiang Yan

Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…

Machine Learning · Computer Science 2022-11-22 Samah Baraheem , Zhongmei Yao

How can agents exchange information to learn while protecting privacy? Healthcare centers collaborating on clinical trials must balance knowledge sharing with safeguarding sensitive patient data. We address this challenge by using…

Machine Learning · Computer Science 2025-03-19 Marios Papachristou , M. Amin Rahimian

In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a critical vulnerability to backdoor attacks, where adversaries can…

Machine Learning · Computer Science 2025-07-03 Zhiyao Ren , Siyuan Liang , Aishan Liu , Dacheng Tao

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training…

Machine Learning · Computer Science 2020-10-12 Fangyuan Zhao , Xuebin Ren , Shusen Yang , Qing Han , Peng Zhao , Xinyu Yang

Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing their ability to produce machine models with high quality predictions. In this work, we empirically evaluate various implementations of…

Cryptography and Security · Computer Science 2020-09-16 Benjamin Zi Hao Zhao , Mohamed Ali Kaafar , Nicolas Kourtellis

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

Machine Learning · Computer Science 2024-07-11 Zachary Charles , Arun Ganesh , Ryan McKenna , H. Brendan McMahan , Nicole Mitchell , Krishna Pillutla , Keith Rush

In-context learning (ICL) is a recent advancement in the capabilities of large language models (LLMs). This feature allows users to perform a new task without updating the model. Concretely, users can address tasks during the inference time…

Cryptography and Security · Computer Science 2024-07-10 Wai Man Si , Michael Backes , Yang 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

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…

Machine Learning · Computer Science 2024-05-06 Fan Wu , Huseyin A. Inan , Arturs Backurs , Varun Chandrasekaran , Janardhan Kulkarni , Robert Sim