English
Related papers

Related papers: Robust Single-message Shuffle Differential Privacy…

200 papers

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

Cryptography and Security · Computer Science 2025-06-25 Saeed Mahloujifar , Chuan Guo , G. Edward Suh , Kamalika Chaudhuri

Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-identification, attribute inference, and data reconstruction --…

Ensuring reliability in adversarial settings necessitates treating privacy as a foundational component of data-driven systems. While differential privacy and cryptographic protocols offer strong guarantees, existing schemes rely on a fixed…

Cryptography and Security · Computer Science 2026-04-10 Labani Halder , Payel Sadhukhan , Sarbani Palit

In this paper, we study the problem of publishing a stream of real-valued data satisfying differential privacy (DP). One major challenge is that the maximal possible value can be quite large; thus it is necessary to estimate a threshold so…

Cryptography and Security · Computer Science 2023-12-11 Tianhao Wang , Joann Qiongna Chen , Zhikun Zhang , Dong Su , Yueqiang Cheng , Zhou Li , Ninghui Li , Somesh Jha

Mobile apps and location-based services generate large amounts of location data that can benefit research on traffic optimization, context-aware notifications and public health (e.g., spread of contagious diseases). To preserve individual…

Databases · Computer Science 2021-08-04 Sepanta Zeighami , Ritesh Ahuja , Gabriel Ghinita , Cyrus Shahabi

Differential Privacy (DP) is a probabilistic framework that protects privacy while preserving data utility. To protect the privacy of the individuals in the dataset, DP requires adding a precise amount of noise to a statistic of interest;…

Computation · Statistics 2025-05-05 Yu-Wei Chen , Pranav Sanghi , Jordan Awan

Differentially private distributed mean estimation (DP-DME) is a fundamental building block in privacy-preserving federated learning, where a central server estimates the mean of $d$-dimensional vectors held by $n$ users while ensuring…

Information Theory · Computer Science 2025-01-09 Sajani Vithana , Viveck R. Cadambe , Flavio P. Calmon , Haewon Jeong

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

Cryptography and Security · Computer Science 2020-09-16 NhatHai Phan , My T. Thai , Han Hu , Ruoming Jin , Tong Sun , Dejing Dou

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

Machine Learning · Computer Science 2026-02-04 Yinan Huang , Haoteng Yin , Eli Chien , Rongzhe Wei , Pan Li

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…

Cryptography and Security · Computer Science 2026-02-09 Tim Kutta , Martin Dunsche , Yu Wei , Vassilis Zikas

Ishai et al. (FOCS'06) introduced secure shuffling as an efficient building block for private data aggregation. Recently, the field of differential privacy has revived interest in secure shufflers by highlighting the privacy amplification…

Cryptography and Security · Computer Science 2025-12-02 Marc Damie , Florian Hahn , Andreas Peter , Jan Ramon

When collecting information, local differential privacy (LDP) relieves the concern of privacy leakage from users' perspective, as user's private information is randomized before sent to the aggregator. We study the problem of recovering the…

Cryptography and Security · Computer Science 2019-12-04 Zitao Li , Tianhao Wang , Milan Lopuhaä-Zwakenberg , Boris Skoric , Ninghui Li

We propose an adaptive (stochastic) gradient perturbation method for differentially private empirical risk minimization. At each iteration, the random noise added to the gradient is optimally adapted to the stepsize; we name this process…

Machine Learning · Computer Science 2021-10-26 Xiaoxia Wu , Lingxiao Wang , Irina Cristali , Quanquan Gu , Rebecca Willett

Data streams collected from multiple sources are rarely independent. Values evolve over time and influence one another across sequences. These correlations improve prediction in healthcare, finance, and smart-city control yet violate the…

Cryptography and Security · Computer Science 2025-11-25 Yifan Luo , Meng Zhang , Jin Xu , Junting Chen , Jianwei Huang

Local differential privacy (LDP) has recently gained prominence as a powerful paradigm for collecting and analyzing sensitive data from users' devices. However, the inherent perturbation added by LDP protocols reduces the utility of the…

Cryptography and Security · Computer Science 2025-07-09 Alireza Khodaie , Berkay Kemal Balioglu , Mehmet Emre Gursoy

Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several noise-aware approaches have been proposed which integrate…

Machine Learning · Statistics 2026-05-29 Talal Alrawajfeh , Joonas Jälkö , Antti Honkela

Extended differential privacy, a generalization of standard differential privacy (DP) using a general metric, has been widely studied to provide rigorous privacy guarantees while keeping high utility. However, existing works on extended DP…

Cryptography and Security · Computer Science 2023-07-19 Natasha Fernandes , Yusuke Kawamoto , Takao Murakami

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Machine Learning · Computer Science 2026-05-22 Aman Saxena , Jan Schuchardt , Yan Scholten , Stephan Günnemann

Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling. However, such randomness is difficult to take into account when proving…

Machine Learning · Statistics 2023-11-02 Chendi Wang , Buxin Su , Jiayuan Ye , Reza Shokri , Weijie J. Su

We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of…

Machine Learning · Computer Science 2024-06-07 Lynn Chua , Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang