English
Related papers

Related papers: Training Set Reconstruction from Differentially Pr…

200 papers

Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achieving a greater…

Machine Learning · Computer Science 2021-10-08 Minseok Ryu , Kibaek Kim

Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising…

Machine Learning · Computer Science 2025-01-22 David Zagardo

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Machine Learning · Computer Science 2026-03-04 Caihong Qin , Yang Bai

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Machine Learning · Computer Science 2025-02-17 Dariush Wahdany , Matthew Jagielski , Adam Dziedzic , Franziska Boenisch

With the randomization approach, sensitive data items of records are randomized to protect privacy of individuals while allowing the distribution information to be reconstructed for data analysis. In this paper, we distinguish between…

Databases · Computer Science 2012-02-16 Ke Wang , Chao Han , Ada Waichee Fu

Differential Privacy (DP) is a mathematical framework that is increasingly deployed to mitigate privacy risks associated with machine learning and statistical analyses. Despite the growing adoption of DP, its technical privacy parameters do…

Cryptography and Security · Computer Science 2024-05-06 Rachel Cummings , Shlomi Hod , Jayshree Sarathy , Marika Swanberg

While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. Differential privacy (DP) is often employed to address such issues.…

Networking and Internet Architecture · Computer Science 2025-12-03 Evan Chen , Frank Po-Chen Lin , Dong-Jun Han , Christopher G. Brinton

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been…

Machine Learning · Computer Science 2025-06-23 Felix Zhou , Samson Zhou , Vahab Mirrokni , Alessandro Epasto , Vincent Cohen-Addad

Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this setting, a subset of the features is known to the attacker…

Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-management paradigm leaves LDPFL vulnerable to participants…

Cryptography and Security · Computer Science 2025-09-08 Zijian Wang , Wei Tong , Tingxuan Han , Haoyu Chen , Tianling Zhang , Yunlong Mao , Sheng Zhong

The combination of deep neural networks and Differential Privacy has been of increasing interest in recent years, as it offers important data protection guarantees to the individuals of the training datasets used. However, using…

Machine Learning · Computer Science 2021-06-03 Osvald Frisk , Friedrich Dörmann , Christian Marius Lillelund , Christian Fischer Pedersen

The private collection of multiple statistics from a population is a fundamental statistical problem. One possible approach to realize this is to rely on the local model of differential privacy (LDP). Numerous LDP protocols have been…

Cryptography and Security · Computer Science 2023-08-02 Héber H. Arcolezi , Sébastien Gambs , Jean-François Couchot , Catuscia Palamidessi

We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models. Previous research has demonstrated that differential privacy (DP)…

Cryptography and Security · Computer Science 2023-07-11 Georgios Kaissis , Jamie Hayes , Alexander Ziller , Daniel Rueckert

We consider supervised learning with random decision trees, where the tree construction is completely random. The method is popularly used and works well in practice despite the simplicity of the setting, but its statistical mechanism is…

Machine Learning · Computer Science 2015-02-06 Mariusz Bojarski , Anna Choromanska , Krzysztof Choromanski , Yann LeCun

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

Machine Learning · Computer Science 2019-07-08 Yuzhe Ma , Xiaojin Zhu , Justin Hsu

Protecting personal data about individuals, such as event traces in process mining, is an inherently difficult task since an event trace leaks information about the path in a process model that an individual has triggered. Yet, prior…

Cryptography and Security · Computer Science 2024-10-07 Max Schulze , Yorck Zisgen , Moritz Kirschte , Esfandiar Mohammadi , Agnes Koschmider

Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been…

Training deep neural networks (DNNs) for meaningful differential privacy (DP) guarantees severely degrades model utility. In this paper, we demonstrate that the architecture of DNNs has a significant impact on model utility in the context…

Machine Learning · Computer Science 2021-10-20 Anda Cheng , Jiaxing Wang , Xi Sheryl Zhang , Qiang Chen , Peisong Wang , Jian Cheng

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The…

Machine Learning · Statistics 2017-05-30 Mikko Heikkilä , Eemil Lagerspetz , Samuel Kaski , Kana Shimizu , Sasu Tarkoma , Antti Honkela

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