English
Related papers

Related papers: Defending against Reconstruction Attacks with R\'e…

200 papers

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the R\'enyi differential privacy of stochastic gradient descent when each training example is…

Machine Learning · Computer Science 2020-02-18 Eloïse Berthier , Sai Praneeth Karimireddy

Differential Privacy (DP) is the leading approach to privacy preserving deep learning. As such, there are multiple efforts to provide drop-in integration of DP into popular frameworks. These efforts, which add noise to each gradient…

Machine Learning · Statistics 2021-06-08 Mathias Lécuyer

We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and…

Information Theory · Computer Science 2020-01-17 Shahab Asoodeh , Jiachun Liao , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

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

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…

Cryptography and Security · Computer Science 2025-03-25 Sheng Liu , Zihan Wang , Yuxiao Chen , Qi Lei

This study investigates embedding reconstruction attacks in large language models (LLMs) applied to genomic sequences, with a specific focus on how fine-tuning affects vulnerability to these attacks. Building upon Pan et al.'s seminal work…

Machine Learning · Computer Science 2025-11-12 Reem Al-Saidi , Erman Ayday , Ziad Kobti

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

Machine Learning · Computer Science 2021-09-07 Ashly Lau , Jonathan Passerat-Palmbach

Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can…

Computation and Language · Computer Science 2024-11-28 Xueluan Gong , Yuji Wang , Shuaike Li , Mengyuan Sun , Songze Li , Qian Wang , Kwok-Yan Lam , Chen Chen

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

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

Machine Learning · Computer Science 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…

Machine Learning · Computer Science 2025-10-14 Tejash Varsani

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Machine Learning · Computer Science 2022-06-03 Yuxuan Wan , Han Xu , Xiaorui Liu , Jie Ren , Wenqi Fan , Jiliang Tang

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

Decentralised learning has recently gained traction as an alternative to federated learning in which both data and coordination are distributed. To preserve the confidentiality of users' data, decentralised learning relies on differential…

Cryptography and Security · Computer Science 2024-12-03 Florine W. Dekker , Zekeriya Erkin , Mauro Conti

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Machine Learning · Statistics 2019-08-27 Liwei Song , Reza Shokri , Prateek Mittal

We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training…

Machine Learning · Computer Science 2022-03-09 Seng Pei Liew , Tsubasa Takahashi , Michihiko Ueno

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

Machine Learning · Statistics 2018-12-21 Martín Abadi , Andy Chu , Ian Goodfellow , H. Brendan McMahan , Ilya Mironov , Kunal Talwar , Li Zhang

Differential privacy offers formal quantitative guarantees for algorithms over datasets, but it assumes attackers that know and can influence all but one record in the database. This assumption often vastly overapproximates the attackers'…

Cryptography and Security · Computer Science 2020-12-01 Damien Desfontaines , Esfandiar Mohammadi , Elisabeth Krahmer , David Basin

In machine learning, privacy requirements at inference or deployment time often evolve due to changing policies, regulations, or user preferences. In this work, we aim to construct a magnitude of models to satisfy any target differential…

Machine Learning · Computer Science 2026-05-21 Qichuan Yin , Manzil Zaheer , Tian Li

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

Cryptography and Security · Computer Science 2023-11-27 Gopichandh Golla