English
Related papers

Related papers: Improving Differentially Private Models with Activ…

200 papers

The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private model degrades the utility drastically when the model…

Machine Learning · Computer Science 2021-10-13 Da Yu , Huishuai Zhang , Wei Chen , Tie-Yan Liu

Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified…

Machine Learning · Computer Science 2024-12-23 Jiapeng Wu , Atiyeh Ashari Ghomi , David Glukhov , Jesse C. Cresswell , Franziska Boenisch , Nicolas Papernot

Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a…

Machine Learning · Computer Science 2021-01-13 Milad Nasr , Shuang Song , Abhradeep Thakurta , Nicolas Papernot , Nicholas Carlini

We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the…

Machine Learning · Computer Science 2025-08-26 Zihang Xiang , Tianhao Wang , Chenglong Wang , Di Wang

Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a…

Machine Learning · Computer Science 2024-05-27 Puning Zhao , Rongfei Fan , Huiwen Wu , Qingming Li , Jiafei Wu , Zhe Liu

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson

Standard methods for differentially private training of deep neural networks replace back-propagated mini-batch gradients with biased and noisy approximations to the gradient. These modifications to training often result in a…

Machine Learning · Computer Science 2020-10-09 Jaewoo Lee , Daniel Kifer

Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain…

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

Cryptography and Security · Computer Science 2021-11-30 Tamara T. Mueller , Alexander Ziller , Dmitrii Usynin , Moritz Knolle , Friederike Jungmann , Daniel Rueckert , Georgios Kaissis

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…

Machine Learning · Computer Science 2025-11-20 Mathieu Dufour , Andrew Duncan

Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While differential privacy…

Computation and Language · Computer Science 2024-08-19 Lynn Chua , Badih Ghazi , Yangsibo Huang , Pritish Kamath , Ravi Kumar , Daogao Liu , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability…

Cryptography and Security · Computer Science 2018-04-24 NhatHai Phan , Xintao Wu , Han Hu , Dejing Dou

Recent work on Renyi Differential Privacy has shown the feasibility of applying differential privacy to deep learning tasks. Despite their promise, however, differentially private deep networks often lag far behind their non-private…

Machine Learning · Computer Science 2020-09-08 Jaewoo Lee , Daniel Kifer

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…

Computation and Language · Computer Science 2022-10-28 Weiyan Shi , Ryan Shea , Si Chen , Chiyuan Zhang , Ruoxi Jia , Zhou Yu

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the…

Machine Learning · Computer Science 2024-11-11 Bogdan Kulynych , Juan Felipe Gomez , Georgios Kaissis , Flavio du Pin Calmon , Carmela Troncoso

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework,…

Machine Learning · Computer Science 2020-03-03 Lichao Sun , Yingbo Zhou , Philip S. Yu , Caiming Xiong

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

Scalability is a significant challenge when it comes to applying differential privacy to training deep neural networks. The commonly used DP-SGD algorithm struggles to maintain a high level of privacy protection while achieving high…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Kamil Adamczewski , Yingchen He , Mijung Park

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

Cryptography and Security · Computer Science 2020-09-04 Lingjuan Lyu , Yee Wei Law , Kee Siong Ng , Shibei Xue , Jun Zhao , Mengmeng Yang , Lei Liu

To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…

Cryptography and Security · Computer Science 2021-03-11 Ho Bae , Jaehee Jang , Dahuin Jung , Hyemi Jang , Heonseok Ha , Hyungyu Lee , Sungroh Yoon