More Like this

1. Private Hierarchical Clustering and Efficient Approximation

   https://doi.org/10.1145/3474123.3486760  

   Meng, Xianrui; Papadopoulos, Dimitrios; Oprea, Alina; Triandopoulos, Nikos (November 2021, CCSW '21: Proceedings of the 2021 on Cloud Computing Security Workshop)

   In collaborative learning, multiple parties contribute their datasets to jointly deduce global machine learning models for numerous predictive tasks. Despite its efficacy, this learning paradigm fails to encompass critical application domains that involve highly sensitive data, such as healthcare and security analytics, where privacy risks limit entities to individually train models using only their own datasets. In this work, we target privacy-preserving collaborative hierarchical clustering. We introduce a formal security definition that aims to achieve balance between utility and privacy and present a two-party protocol that provably satisfies it. We then extend our protocol with: (i) an optimized version for single-linkage clustering, and (ii) scalable approximation variants. We implement all our schemes and experimentally evaluate their performance and accuracy on synthetic and real datasets, obtaining very encouraging results. For example, end-to-end execution of our secure approximate protocol for over 1M 10-dimensional data samples requires 35sec of computation and achieves 97.09% accuracy. 

   more » « less
2. Privacy-Preserving Self-Supervised Learning for Secure Image Processing: A BYOL-Based Framework for MNIST and Chest X-ray Data

   Riad, ABM Kamrul; Salma, Ahmed; Nizum, Maliha; Barek, Md; Rashid, Md; Rahman, Md Mostafizur; Francia, Guillermo; Shahriar, Hossain (July 2025, IEEE)

   The increasing use of high-dimensional imaging in medical AI raises significant privacy and security concerns. This paper presents a Bootstrap Your Own Latent (BYOL)-based self supervised learning (SSL) framework for secure image processing, ensuring compliance with HIPAA and privacy-preserving machine learning (PPML) techniques. Our method integrates federated learning, homomorphic encryption, and differential privacy to enhance security while reducing dependence on labeled data. Experimental results on the MNIST and NIH Chest Xray datasets demonstrate a classification accuracy of 97.5% and 99.99% (pre-fine-tuning 40%), with improved clustering performance using K-Means (Silhouette Score: 0.5247). These findings validate BYOL’s capability for robust, privacy-preserving image processing while emphasizing the need for fine-tuning to optimize classification performance. 

   more » « less
3. ELSA: Secure Aggregation for Federated Learning with Malicious Actors

   Rathee, Mayank; Shen, Conghao; Wagh, Sameer; Popa, Raluca Ada (January 2023, Proceedings of the IEEE Symposium on Security and Privacy)

   Federated learning (FL) is an increasingly popular approach for machine learning (ML) in cases where the training dataset is highly distributed. Clients perform local training on their datasets and the updates are then aggregated into the global model. Existing protocols for aggregation are either inefficient, or don’t consider the case of malicious actors in the system. This is a major barrier in making FL an ideal solution for privacy-sensitive ML applications. We present ELSA, a secure aggregation protocol for FL, which breaks this barrier - it is efficient and addresses the existence of malicious actors at the core of its design. Similar to prior work on Prio and Prio+, ELSA provides a novel secure aggregation protocol built out of distributed trust across two servers that keeps individual client updates private as long as one server is honest, defends against malicious clients, and is efficient end-to-end. Compared to prior works, the distinguishing theme in ELSA is that instead of the servers generating cryptographic correlations interactively, the clients act as untrusted dealers of these correlations without compromising the protocol’s security. This leads to a much faster protocol while also achieving stronger security at that efficiency compared to prior work. We introduce new techniques that retain privacy even when a server is malicious at a small added cost of 7-25% in runtime with negligible increase in communication over the case of semi-honest server. Our work improves end-to-end runtime over prior work with similar security guarantees by big margins - single-aggregator RoFL by up to 305x (for the models we consider), and distributed trust Prio by up to 8x. 

   more » « less
4. Decentralized and Secure Collaborative Framework for Personalized Diabetes Prediction

   https://doi.org/10.3390/biomedicines12081916  

   Hasan, Md Rakibul; Li, Qingrui; Saha, Utsha; Li, Juan (August 2024, Biomedicines)

   Diabetes is a global epidemic with severe consequences for individuals and healthcare systems. While early and personalized prediction can significantly improve outcomes, traditional centralized prediction models suffer from privacy risks and limited data diversity. This paper introduces a novel framework that integrates blockchain and federated learning to address these challenges. Blockchain provides a secure, decentralized foundation for data management, access control, and auditability. Federated learning enables model training on distributed datasets without compromising patient privacy. This collaborative approach facilitates the development of more robust and personalized diabetes prediction models, leveraging the combined data resources of multiple healthcare institutions. We have performed extensive evaluation experiments and security analyses. The results demonstrate good performance while significantly enhancing privacy and security compared to centralized approaches. Our framework offers a promising solution for the ethical and effective use of healthcare data in diabetes prediction. 

   more » « less
5. ELSA: Secure Aggregation for Federated Learning with Malicious Actors

   Rathee, Mayank; Shen, Conghao; Wagh, Sameer; Popa, Raluca Ada (January 2023, Proceedings of the IEEE Symposium on Security and Privacy)

   Federated learning (FL) is an increasingly popular approach for machine learning (ML) when the training dataset is highly distributed. Clients perform local training on their datasets and the updates are then aggregated into the global model. Existing protocols for aggregation are either inefficient or don’t consider the case of malicious actors in the system. This is a major barrier to making FL an ideal solution for privacy-sensitive ML applications. In this talk, I will present ELSA, a secure aggregation protocol for FL that breaks this barrier - it is efficient and addresses the existence of malicious actors (clients + servers) at the core of its design. Similar to prior work Prio and Prio+, ELSA provides a novel secure aggregation protocol built out of distributed trust across two servers that keeps individual client updates private as long as one server is honest, defends against malicious clients, and is efficient end-to-end. Compared to prior works, the distinguishing theme in ELSA is that instead of the servers generating cryptographic correlations interactively, the clients act as untrusted dealers of these correlations without compromising the protocol’s security. This leads to a much faster protocol while also achieving stronger security at that efficiency compared to prior work. We introduce new techniques that retain privacy even when a server is malicious at a small added cost of 7-25% in runtime with a negligible increase in communication over the case of a semi-honest server. ELSA improves end-to-end runtime over prior work with similar security guarantees by big margins - single-aggregator RoFL by up to 305x (for the models we consider), and distributed-trust Prio by up to 8x (with up to 16x faster server-side protocol). Additionally, ELSA can be run in a bandwidth-saver mode for clients who are geographically bandwidth-constrained - an important property that is missing from prior works. 

   more » « less