Related papers: TAPAS: Efficient Two-Server Asymmetric Private Agg…

Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive information through inference attacks. Secure aggregation…

With changes in privacy laws, there is often a hard requirement for client data to remain on the device rather than being sent to the server. Therefore, most processing happens on the device, and only an altered element is sent to the…

Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing dimensionality reduced representations of data has been…

Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization…

Training machine learning models on data from multiple entities without direct data sharing can unlock applications otherwise hindered by business, legal, or ethical constraints. In this work, we design and implement new privacy-preserving…

As data-driven and AI-based decision making gains widespread adoption across disciplines, it is crucial that both data privacy and decision fairness are appropriately addressed. Although differential privacy (DP) provides a robust framework…

We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited…

We consider the critical problem of distributed learning over data while keeping it private from the computational servers. The state-of-the-art approaches to this problem rely on quantizing the data into a finite field, so that the…

With the onset of the Information Era and the rapid growth of information technology, ample space for processing and extracting data has opened up. However, privacy concerns may stifle expansion throughout this area. The challenge of…

Tensor parallelism is an essential technique for distributed training of large neural networks. However, automatically determining an optimal tensor parallel strategy is challenging due to the gigantic search space, which grows…

For population studies or for the training of complex machine learning models, it is often required to gather data from different actors. In these applications, summation is an important primitive: for computing means, counts or mini-batch…

We introduce baseSPIDER and SPIDER, private information retrieval (PIR) schemes that embody two technical advancements. The baseSPIDER protocol operates with a single server and a stateful client that performs pre-processing and stores…

TAPS is a Topology-Aware intra-operator Parallelism strategy Searching algorithm that generates intra-operator parallelism strategies by considering both intra-node and inter-node bandwidth. Most of the existing auto-parallelism works use…

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…

In federated learning (FL), local personalization of models has received significant attention, yet personalized fine-tuning of foundation models remains underexplored. In particular, there is a lack of understanding in the literature on…

Nonlinear aggregation is central to modern distributed systems, yet its privacy behavior is far less understood than that of linear aggregation. Unlike linear aggregation where mature mechanisms can often suppress information leakage,…

Duplication can be a powerful strategy for overcoming stragglers in cloud services, but is often used conservatively because of the risk of overloading the system. We present duplicate-aware scheduling or DAS, which makes duplication safe…

Privacy-preserving federated averaging is a central approach for protecting client privacy in federated learning. In this paper, we study this problem in an asynchronous communications setting with malicious aggregators. We propose a new…

Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these challenges in isolation, sacrificing accuracy, relying on…

We propose a new computationally efficient privacy-preserving identification framework based on layered sparse coding. The key idea of the proposed framework is a sparsifying transform learning with ambiguization, which consists of a…