English
Related papers

Related papers: Precision-based attacks and interval refining: how…

200 papers

This paper considers the private release of statistics of disjoint subsets of a dataset, in the setting of data heterogeneity, where users could contribute more than one sample, with different users contributing potentially different…

Cryptography and Security · Computer Science 2025-03-26 V. Arvind Rameshwar , Anshoo Tandon

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Cryptography and Security · Computer Science 2021-10-13 Jiaxiang Liu , Simon Oya , Florian Kerschbaum

Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct…

Machine Learning · Computer Science 2021-12-28 Wenqi Wei , Ling Liu

The calibration of noise for a privacy-preserving mechanism depends on the sensitivity of the query and the prescribed privacy level. A data steward must make the non-trivial choice of a privacy level that balances the requirements of users…

Cryptography and Security · Computer Science 2020-04-15 Ashish Dandekar , Debabrota Basu , Stephane Bressan

Being able to efficiently and accurately select the top-$k$ elements with differential privacy is an integral component of various private data analysis tasks. In this paper, we present the oneshot Laplace mechanism, which generalizes the…

Machine Learning · Computer Science 2021-06-24 Gang Qiao , Weijie J. Su , Li Zhang

Differential privacy is one of the methods to solve the problem of privacy protection in federated learning. Setting the same privacy budget for each round will result in reduced accuracy in training. The existing methods of the adjustment…

Cryptography and Security · Computer Science 2024-08-20 Zhiqiang Wang , Xinyue Yu , Qianli Huang , Yongguang Gong

The Laplace mechanism is the workhorse of differential privacy, applied to many instances where numerical data is processed. However, the Laplace mechanism can return semantically impossible values, such as negative counts, due to its…

Cryptography and Security · Computer Science 2018-08-31 Naoise Holohan , Spiros Antonatos , Stefano Braghin , Pól Mac Aonghusa

How to properly set the privacy parameter in differential privacy (DP) has been an open question in DP research since it was first proposed in 2006. In this work, we demonstrate the ability of influence functions to offer insight into how a…

Machine Learning · Computer Science 2023-09-19 Alycia N. Carey , Minh-Hao Van , Xintao Wu

Performing low-rank matrix completion with sensitive user data calls for privacy-preserving approaches. In this work, we propose a novel noise addition mechanism for preserving differential privacy where the noise distribution is inspired…

Cryptography and Security · Computer Science 2022-06-17 R Adithya Gowtham , Gokularam M , Thulasi Tholeti , Sheetal Kalyani

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

In the post-industrial world, data science and analytics have gained paramount importance regarding digital data privacy. Improper methods of establishing privacy for accessible datasets can compromise large amounts of user data even if the…

Machine Learning · Computer Science 2020-02-20 Kenneth Choi , Tony Lee

Graph diffusion, which iteratively propagates real-valued substances among the graph, is used in numerous graph/network-involved applications. However, releasing diffusion vectors may reveal sensitive linking information in the data such as…

Information Retrieval · Computer Science 2025-02-19 Rongzhe Wei , Eli Chien , Pan Li

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

In this paper, we present a comprehensive framework for differential privacy over affine manifolds and validate its usefulness in the contexts of differentially private cloud-based control and average consensus. We consider differential…

Systems and Control · Electrical Eng. & Systems 2026-01-22 Zihao Ren , Lei Wang , Deming Yuan , Guodong Shi

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Machine Learning · Computer Science 2026-01-19 Lele Zheng , Xiang Wang , Tao Zhang , Yang Cao , Ke Cheng , Yulong Shen

The Gaussian mechanism is an essential building block used in multitude of differentially private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show that the original analysis has several important…

Machine Learning · Computer Science 2018-06-08 Borja Balle , Yu-Xiang Wang

Currently known methods for this task either employ the computationally intensive \emph{exponential mechanism} or require an access to the covariance matrix, and therefore fail to utilize potential sparsity of the data. The problem of…

Machine Learning · Computer Science 2020-03-03 Ran Gilad-Bachrach , Alon Gonen

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Cryptography and Security · Computer Science 2024-02-27 Nikhil Kandpal , Krishna Pillutla , Alina Oprea , Peter Kairouz , Christopher A. Choquette-Choo , Zheng Xu

NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget $\epsilon$. However, $\epsilon$ does not have any intrinsic meaning, and it is…

Machine Learning · Computer Science 2025-03-19 Pedro Faustini , Natasha Fernandes , Annabelle McIver , Mark Dras

Data is continuously generated by modern data sources, and a recent challenge in machine learning has been to develop techniques that perform well in an incremental (streaming) setting. In this paper, we investigate the problem of private…

Data Structures and Algorithms · Computer Science 2017-01-05 Shiva Prasad Kasiviswanathan , Kobbi Nissim , Hongxia Jin