More Like this

1. Polymath: Low-Latency MPC via Secure Polynomial Evaluations and Its Applications

   https://doi.org/10.2478/popets-2022-0020  

   Lu, Donghang; Yu, Albert; Kate, Aniket; Maji, Hemanta (November 2021, Proceedings on Privacy Enhancing Technologies)

   Abstract While the practicality of secure multi-party computation (MPC) has been extensively analyzed and improved over the past decade, we are hitting the limits of efficiency with the traditional approaches of representing the computed functionalities as generic arithmetic or Boolean circuits. This work follows the design principle of identifying and constructing fast and provably-secure MPC protocols to evaluate useful high-level algebraic abstractions; thus, improving the efficiency of all applications relying on them. We present Polymath, a constant-round secure computation protocol suite for the secure evaluation of (multi-variate) polynomials of scalars and matrices, functionalities essential to numerous data-processing applications. Using precise natural precomputation and high-degree of parallelism prevalent in the modern computing environments, Polymath can make latency of secure polynomial evaluations of scalars and matrices independent of polynomial degree and matrix dimensions. We implement our protocols over the HoneyBadgerMPC library and apply it to two prominent secure computation tasks: privacy-preserving evaluation of decision trees and privacy-preserving evaluation of Markov processes. For the decision tree evaluation problem, we demonstrate the feasibility of evaluating high-depth decision tree models in a general n -party setting. For the Markov process application, we demonstrate that Poly-math can compute large powers of transition matrices with better online time and less communication. 

   more » « less
2. Privacy-preserving logistic regression with secret sharing

   https://doi.org/10.1186/s12911-022-01811-y  

   Ghavamipour, Ali Reza; Turkmen, Fatih; Jiang, Xiaoqian (December 2022, BMC Medical Informatics and Decision Making)

   Abstract Background Logistic regression (LR) is a widely used classification method for modeling binary outcomes in many medical data classification tasks. Researchers that collect and combine datasets from various data custodians and jurisdictions can greatly benefit from the increased statistical power to support their analysis goals. However, combining data from different sources creates serious privacy concerns that need to be addressed. Methods In this paper, we propose two privacy-preserving protocols for performing logistic regression with the Newton–Raphson method in the estimation of parameters. Our proposals are based on secure Multi-Party Computation (MPC) and tailored to the honest majority and dishonest majority security settings. Results The proposed protocols are evaluated against both synthetic and real-world datasets in terms of efficiency and accuracy, and a comparison is made with the ordinary logistic regression. The experimental results demonstrate that the proposed protocols are highly efficient and accurate. Conclusions Our work introduces two iterative algorithms to enable the distributed training of a logistic regression model in a privacy-preserving manner. The implementation results show that our algorithms can handle large datasets from multiple sources. 

   more » « less
3. Generating Connected Synthetic Electronic Health Records and Social Media Data for Modeling and Simulation

   Tall, Anne M.; Zou, Cliff C.; Wang, Jun (December 2020, Interservice/Industry Training, Simulation and Education Conference (I/ITSEC))

   null (Ed.)

   Research and experimentation using big data sets, specifically large sets of electronic health records (EHR) and social media data, is demonstrating the potential to understand the spread of diseases and a variety of other issues. Applications of advanced algorithms, machine learning, and artificial intelligence indicate a potential for rapidly advancing improvements in public health. For example, several reports indicate that social media data can be used to predict disease outbreak and spread (Brown, 2015). Since real-world EHR data has complicated security and privacy issues preventing it from being widely used by researchers, there is a real need to synthetically generate EHR data that is realistic and representative. Current EHR generators, such as Syntheaä (Walonoski et al., 2018) only simulate and generate pure medical-related data. However, adding patients’ social media data with their simulated EHR data would make combined data more comprehensive and realistic for healthcare research. This paper presents a patients’ social media data generator that extends an EHR data generator. By adding coherent social media data to EHR data, a variety of issues can be examined for emerging interests, such as where a contagious patient may have been and others with whom they may have been in contact. Social media data, specifically Twitter data, is generated with phrases indicating the onset of symptoms corresponding to the synthetically generated EHR reports of simulated patients. This enables creation of an open data set that is scalable up to a big-data size, and is not subject to the security, privacy concerns, and restrictions of real healthcare data sets. This capability is important to the modeling and simulation community, such as scientists and epidemiologists who are developing algorithms to analyze the spread of diseases. It enables testing a variety of analytics without revealing real-world private patient information. 

   more » « less
4. Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware

   https://doi.org/10.56553/popets-2024-0119  

   Huang, Pengzhi; Hoang, Thang; Li, Yueying; Shi, Elaine; Suh, G Edward (October 2024, Proceedings on Privacy Enhancing Technologies)

   In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors. Our platform provides three main advantages over the state-of-the-art: (i) We achieve significant performance improvements compared to state-of-the-art distributed Privacy-Preserving Machine Learning (PPML) protocols, with only a small security processor that is comparable to a discrete security chip such as the Trusted Platform Module (TPM) or on-chip security subsystems in SoCs similar to the Apple enclave processor. In the semi-honest setting with WAN/GPU, our scheme is 4X-63X faster than Falcon (PoPETs'21) and AriaNN (PoPETs'22) and 3.8X-12X more communication efficient. We achieve even higher performance improvements in the malicious setting. (ii) Our platform guarantees security with abort against malicious adversaries under honest majority assumption. (iii) Our technique is not limited by the size of secure memory in a TEE and can support high-capacity modern neural networks like ResNet18 and Transformer. While previous work investigated the use of high-performance TEEs in PPML, this work represents the first to show that even tiny secure hardware with very limited performance can be leveraged to significantly speed-up distributed PPML protocols if the protocol can be carefully designed for lightweight trusted hardware. 

   more » « less
5. Lost in Translation: Exploring the Risks of Web-to-Cross-platform Application Migration

   https://doi.org/10.56553/popets-2025-0117  

   Paloscia, Claudio; Solomos, Kostas; Ali, Mir Masood; Polakis, Jason (October 2025, Proceedings on Privacy Enhancing Technologies)

   The cross-platform application-development paradigm alleviates a major challenge of native application development, namely the need to re-implement the codebase for each target platform, and streamlines the deployment of applications to different platforms. Essentially, cross-platform application development relies on migrating web application code and repackaging it as a native application. In other words, code that was designed and developed to execute within the confines of a browser, with all the security checks and safeguards that that entails, is now deployed within a completely different execution environment. In this paper, we explore the inherent security and privacy risks that arise from this migration, due to the fundamental differences between these two execution environments, which we refer to as security lacunae. To that end, we establish a differential analysis workflow and develop a set of customized tests designed to uncover divergent behaviors of web code executed within a browser and as an Electron cross-platform application. Guided by the findings from our empirical exploration, we retrofit part of the Web Platform Tests (WPTs) testing suite so as to apply to the Electron framework, and systematically assess mechanisms that relate to isolation and access control, and critical security policies and headers. Our research uncovers semantic gaps that exist between the two execution environments, which affect the enforcement of critical security mechanisms, thus exposing users to severe risks. This can lead to privacy issues such as the exposure of sensitive data over unencrypted connections or unregulated third-party access to the local filesystem, and security issues such as the incorrect enforcement of CSP script execution directives. We demonstrate that directly migrating web application code to a cross-platform application, without refactoring the code and implementing additional safeguards to address the conceptual and behavioral mismatches between the two execution environments, can significantly affect the application's security and privacy posture. 

   more » « less