English
Related papers

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

200 papers

Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…

Machine Learning · Computer Science 2020-10-27 Gavin Kerrigan , Dylan Slack , Jens Tuyls

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

Cryptography and Security · Computer Science 2022-12-21 Nikhil Kandpal , Eric Wallace , Colin Raffel

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. Without directly interactive with training examples, the generative…

Machine Learning · Computer Science 2020-07-07 Chuan Ma , Jun Li , Ming Ding , Bo Liu , Kang Wei , Jian Weng , H. Vincent Poor

Using a recently proposed privacy definition of R\'enyi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating…

Machine Learning · Computer Science 2017-10-04 Joseph Geumlek , Shuang Song , Kamalika Chaudhuri

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…

Machine Learning · Computer Science 2024-03-14 Guy Amit , Abigail Goldsteen , Ariel Farkash

Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities…

Machine Learning · Computer Science 2025-09-08 Francesco Diana , André Nusser , Chuan Xu , Giovanni Neglia

The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage.…

Cryptography and Security · Computer Science 2020-06-12 Poushali Sengupta , Sudipta Paul , Subhankar Mishra

While pursuing better utility by discovering knowledge from the data, individual's privacy may be compromised during an analysis. To that end, differential privacy has been widely recognized as the state-of-the-art privacy notion. By…

Cryptography and Security · Computer Science 2022-09-07 Meisam Mohammady

Differential privacy (DP) is the de facto standard for private data release and private machine learning. Auditing black-box DP algorithms and mechanisms to certify whether they satisfy a certain DP guarantee is challenging, especially in…

Machine Learning · Computer Science 2022-05-30 Carles Domingo-Enrich , Youssef Mroueh

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

We propose a natural relaxation of differential privacy based on the Renyi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially private mechanisms. We argue that the useful…

Cryptography and Security · Computer Science 2018-12-12 Ilya Mironov

Federated Learning (FL) trains a black-box and high-dimensional model among different clients by exchanging parameters instead of direct data sharing, which mitigates the privacy leak incurred by machine learning. However, FL still suffers…

Machine Learning · Computer Science 2024-03-05 Qi Tan , Qi Li , Yi Zhao , Zhuotao Liu , Xiaobing Guo , Ke Xu

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

Machine Learning · Computer Science 2022-02-09 Ji Gao , Sanjam Garg , Mohammad Mahmoody , Prashant Nalini Vasudevan

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Machine Learning · Computer Science 2025-09-26 Yehonatan Refael , Guy Smorodinsky , Ofir Lindenbaum , Itay Safran

Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial…

Cryptography and Security · Computer Science 2024-04-02 Abdallah Alshantti , Adil Rasheed , Frank Westad

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…

Cryptography and Security · Computer Science 2025-11-13 Tatsuki Koga , Ruihan Wu , Zhiyuan Zhang , Kamalika Chaudhuri

A reconstruction attack on a private dataset $D$ takes as input some publicly accessible information about the dataset and produces a list of candidate elements of $D$. We introduce a new class of data reconstruction attacks based on…

Computers and Society · Computer Science 2023-03-29 Travis Dick , Cynthia Dwork , Michael Kearns , Terrance Liu , Aaron Roth , Giuseppe Vietri , Zhiwei Steven Wu

Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm…

Cryptography and Security · Computer Science 2024-10-08 Junjie Chu , Zeyang Sha , Michael Backes , Yang Zhang

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model…

Machine Learning · Computer Science 2019-11-25 Taihong Xiao , Yi-Hsuan Tsai , Kihyuk Sohn , Manmohan Chandraker , Ming-Hsuan Yang

Federated Learning allows distributed entities to train a common model collaboratively without sharing their own data. Although it prevents data collection and aggregation by exchanging only parameter updates, it remains vulnerable to…

Machine Learning · Computer Science 2020-11-12 Raouf Kerkouche , Gergely Ács , Claude Castelluccia , Pierre Genevès