English
Related papers

Related papers: Privacy Leakage Avoidance with Switching Ensembles

200 papers

Training high-performing deep learning models require a rich amount of data which is usually distributed among multiple data sources in practice. Simply centralizing these multi-sourced data for training would raise critical security and…

Cryptography and Security · Computer Science 2021-10-27 Yansong Gao , Qun Li , Yifeng Zheng , Guohong Wang , Jiannan Wei , Mang Su

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…

Cryptography and Security · Computer Science 2025-06-09 Ruining Sun , Hongsheng Hu , Wei Luo , Zhaoxi Zhang , Yanjun Zhang , Haizhuan Yuan , Leo Yu Zhang

This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks,…

Cryptography and Security · Computer Science 2024-10-02 Carl E. J. Brodzinski

Secure multiparty computation (MPC) has been proposed to allow multiple mutually distrustful data owners to jointly train machine learning (ML) models on their combined data. However, by design, MPC protocols faithfully compute the training…

Cryptography and Security · Computer Science 2022-09-09 Harsh Chaudhari , Matthew Jagielski , Alina Oprea

As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing…

Machine Learning · Computer Science 2022-07-14 Dingfan Chen , Ning Yu , Mario Fritz

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

A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group…

Machine Learning · Computer Science 2022-04-12 Cuong Tran , Keyu Zhu , Ferdinando Fioretto , Pascal Van Hentenryck

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

Machine Learning · Computer Science 2026-04-07 Ganghua Wang , Yuhong Yang , Jie Ding

Privacy-preserving network anomaly detection has become an essential area of research due to growing concerns over the protection of sensitive data. Traditional anomaly detection models often prioritize accuracy while neglecting the…

Machine Learning · Computer Science 2025-02-19 Shaobo Liu , Zihao Zhao , Weijie He , Jiren Wang , Jing Peng , Haoyuan Ma

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Machine Learning · Computer Science 2018-02-20 Aurélien Bellet , Rachid Guerraoui , Mahsa Taziki , Marc Tommasi

We study the membership inference (MI) attack against classifiers, where the attacker's goal is to determine whether a data instance was used for training the classifier. Through systematic cataloging of existing MI attacks and extensive…

Cryptography and Security · Computer Science 2021-02-04 Jiacheng Li , Ninghui Li , Bruno Ribeiro

Machine learning algorithms, however effective, are known to be vulnerable in adversarial scenarios where a malicious user may inject manipulated instances. In this work we focus on evasion attacks, where a model is trained in a safe…

Machine Learning · Computer Science 2020-04-08 Stefano Calzavara , Claudio Lucchese , Federico Marcuzzi , Salvatore Orlando

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Cryptography and Security · Computer Science 2024-04-02 Shanglun Feng , Florian Tramèr

Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model. Knowing this may indeed lead to a privacy breach. Most MIAs, however, make use of the model's prediction scores - the…

Machine Learning · Computer Science 2023-01-25 Dominik Hintersdorf , Lukas Struppek , Kristian Kersting

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…

Machine Learning · Computer Science 2019-08-16 Stacey Truex , Nathalie Baracaldo , Ali Anwar , Thomas Steinke , Heiko Ludwig , Rui Zhang , Yi Zhou

Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…

Cryptography and Security · Computer Science 2025-08-22 Elena Sofia Ruzzetti , Giancarlo A. Xompero , Davide Venditti , Fabio Massimo Zanzotto

As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and…

Cryptography and Security · Computer Science 2024-05-30 Fei Zheng , Chaochao Chen , Lingjuan Lyu , Xinyi Fu , Xing Fu , Weiqiang Wang , Xiaolin Zheng , Jianwei Yin

An attacker can gain information of a user by analyzing its network traffic. The size of transferred data leaks information about the file being transferred or the service being used, and this is particularly revealing when the attacker has…

Cryptography and Security · Computer Science 2022-09-12 Sebastian Simon , Cezara Petrui , Carlos Pinzón , Catuscia Palamidessi

Privacy preserving in machine learning is a crucial issue in industry informatics since data used for training in industries usually contain sensitive information. Existing differentially private machine learning algorithms have not…

Machine Learning · Computer Science 2020-10-08 Tao Zhang , Tianqing Zhu , Ping Xiong , Huan Huo , Zahir Tari , Wanlei Zhou

This work investigates the design of sparse secret sharing schemes that encode a sparse private matrix into sparse shares. This investigation is motivated by distributed computing, where the multiplication of sparse and private matrices is…

Cryptography and Security · Computer Science 2023-08-15 Rawad Bitar , Maximilian Egger , Antonia Wachter-Zeh , Marvin Xhemrishi