Related papers: Samplable Anonymous Aggregation for Private Federa…

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover…

Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…

Federated learning is a distributed framework for training machine learning models over the data residing at mobile devices, while protecting the privacy of individual users. A major bottleneck in scaling federated learning to a large…

Artificial intelligence and data access are already mainstream. One of the main challenges when designing an artificial intelligence or disclosing content from a database is preserving the privacy of individuals who participate in the…

Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent…

In this work, we give a new technique for analyzing individualized privacy accounting via the following simple observation: if an algorithm is one-sided add-DP, then its subsampled variant satisfies two-sided DP. From this, we obtain…

Differentially private triangle counting in graphs is essential for analyzing connection patterns and calculating clustering coefficients while protecting sensitive individual information. Previous works have relied on either central or…

Scalability and privacy are two critical concerns for cross-device federated learning (FL) systems. In this work, we identify that synchronous FL - synchronized aggregation of client updates in FL - cannot scale efficiently beyond a few…

This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The proposed algorithm…

How to preserve users' privacy while supporting high-utility analytics for low-latency stream processing? To answer this question: we describe the design, implementation, and evaluation of PRIVAPPROX, a data analytics system for…

Clustering is a fundamental problem in data analysis. In differentially private clustering, the goal is to identify $k$ cluster centers without disclosing information on individual data points. Despite significant research progress, the…

We consider a problem where mutually untrusting curators possess portions of a vertically partitioned database containing information about a set of individuals. The goal is to enable an authorized party to obtain aggregate (statistical)…

k-Anonymity by microaggregation is one of the most commonly used anonymization techniques. This success is owe to the achievement of a worth of interest tradeoff between information loss and identity disclosure risk. However, this method…

Collective privacy loss becomes a colossal problem, an emergency for personal freedoms and democracy. But, are we prepared to handle personal data as scarce resource and collectively share data under the doctrine: as little as possible, as…

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…

Federated optimization, wherein several agents in a network collaborate with a central server to achieve optimal social cost over the network with no requirement for exchanging information among agents, has attracted significant interest…

Recent work by Pijnenburg and Poettering (ESORICS'20) explores the novel cryptographic Encrypt-to-Self primitive that is dedicated to use cases of symmetric encryption where encryptor and decryptor coincide. The primitive is envisioned to…

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…

Federated learning enables training a global machine learning model from data distributed across multiple sites, without having to move the data. This is particularly relevant in healthcare applications, where data is rife with personal,…