English
Related papers

Related papers: Single-Component Privacy Guarantees in Helper Data…

200 papers

Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To…

Machine Learning · Computer Science 2019-12-10 Hilal Asi , John Duchi , Omid Javidbakht

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes…

Machine Learning · Computer Science 2020-10-27 Han Zhao , Jianfeng Chi , Yuan Tian , Geoffrey J. Gordon

With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…

Machine Learning · Computer Science 2022-02-22 Fei Zheng , Chaochao Chen , Xiaolin Zheng , Mingjie Zhu

It is often necessary to disclose training data to the public domain, while protecting privacy of certain sensitive labels. We use information theoretic measures to develop such privacy preserving data disclosure mechanisms. Our mechanism…

Information Theory · Computer Science 2019-04-08 Tianrui Xiao , Ashish Khisti

We revisit one of the most basic and widely applicable techniques in the literature of differential privacy - the sparse vector technique [Dwork et al., STOC 2009]. This simple algorithm privately tests whether the value of a given query on…

Machine Learning · Computer Science 2020-11-17 Haim Kaplan , Yishay Mansour , Uri Stemmer

This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the sensor data have different underlying…

Machine Learning · Computer Science 2023-10-24 Xin Yang , Omid Ardakanian

Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest or news feed. State-of-the-art recommendation models rely on…

Computational Engineering, Finance, and Science · Computer Science 2022-12-14 Hanieh Hashemi , Wenjie Xiong , Liu Ke , Kiwan Maeng , Murali Annavaram , G. Edward Suh , Hsien-Hsin S. Lee

Biometric systems, while offering convenient authentication, often fall short in providing rigorous security assurances. A primary reason is the ad-hoc design of protocols and components, which hinders the establishment of comprehensive…

Cryptography and Security · Computer Science 2024-11-27 Sam Grierson , William J Buchanan , Craig Thomson , Baraq Galeb , Chris Eckl

In this paper, we propose a new biometric verification and template protection system which we call the THRIVE system. The system includes novel enrollment and authentication protocols based on threshold homomorphic cryptosystem where the…

Cryptography and Security · Computer Science 2015-09-02 Cagatay Karabat , Mehmet Sabir Kiraz , Hakan Erdogan , Erkay Savas

Current research on soft-biometrics showed that privacy-sensitive information can be deduced from biometric templates of an individual. Since for many applications, these templates are expected to be used for recognition purposes only, this…

Computer Vision and Pattern Recognition · Computer Science 2020-02-24 Philipp Terhörst , Marco Huber , Naser Damer , Florian Kirchbuchner , Arjan Kuijper

Our behavior (the way we talk, walk, act or think) is unique and can be used as a biometric trait. It also correlates with sensitive attributes like emotions and health conditions. Hence, techniques to protect individuals privacy against…

Cryptography and Security · Computer Science 2023-01-06 Simon Hanisch , Patricia Arias-Cabarcos , Javier Parra-Arnau , Thorsten Strufe

We investigate the privacy amplification problem in which Eve can observe the uniform binary source through a binary erasure channel (BEC) or a binary symmetric channel (BSC). For this problem, we derive the so-called expurgation exponent…

Information Theory · Computer Science 2016-11-17 Shun Watanabe

For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training run is well understood. However, few studies have reasoned…

Machine Learning · Computer Science 2022-03-15 Nicolas Papernot , Thomas Steinke

In this work, we propose a differentially private algorithm for publishing matrices aggregated from sparse vectors. These matrices include social network adjacency matrices, user-item interaction matrices in recommendation systems, and…

Cryptography and Security · Computer Science 2025-06-26 Quentin Hillebrand , Vorapong Suppakitpaisarn , Tetsuo Shibuya

Using a broadcast channel to transmit clients' data requests may impose privacy risks. In this paper, we address such privacy concerns in the index coding framework. We show how a malicious client can infer some information about the…

Information Theory · Computer Science 2018-10-16 Mohammed Karmoose , Linqi Song , Martina Cardone , Christina Fragouli

Verifiable credentials are a digital analogue of physical credentials. Their authenticity and integrity are protected by means of cryptographic techniques, and they can be presented to verifiers to reveal attributes or even predicates about…

Cryptography and Security · Computer Science 2024-01-17 Andrea Flamini , Giada Sciarretta , Mario Scuro , Amir Sharif , Alessandro Tomasi , Silvio Ranise

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Machine Learning · Computer Science 2024-12-17 Binghui Zhang , Sayedeh Leila Noorbakhsh , Yun Dong , Yuan Hong , Binghui Wang

We consider the problem of designing a coding scheme that allows both sparsity and privacy for distributed matrix-vector multiplication. Perfect information-theoretic privacy requires encoding the input sparse matrices into matrices…

Information Theory · Computer Science 2022-03-04 Marvin Xhemrishi , Rawad Bitar , Antonia Wachter-Zeh

In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, under mild assumptions on the data, provably achieves…

Machine Learning · Computer Science 2023-06-08 Francesco Pinto , Yaxi Hu , Fanny Yang , Amartya Sanyal

We study a semantic communication problem with a privacy constraint where an encoder consists of two separate parts, e.g., encoder 1 and encoder 2. The first encoder has access to information source $X=(X_1,\ldots,X_N)$ which is arbitrarily…

Information Theory · Computer Science 2024-12-24 Amirreza Zamani , Mikael Skoglund
‹ Prev 1 4 5 6 7 8 10 Next ›