This paper studies federated learning (FL)--especially cross-silo FL--with data from people who do not trust the server or other silos. In this setting, each silo (e.g. hospital) has data from different people (e.g. patients) and must maintain the privacy of each person's data (e.g. medical record), even if the server or other silos act as adversarial eavesdroppers. This requirement motivates the study of Inter-Silo Record-Level Differential Privacy (ISRL-DP), which requires silos' communications to satisfy record/item-level differential privacy (DP). ISRL-DP ensures that the data of each person (e.g. patient) in silo i (e.g. hospital i) cannot be leaked. ISRL-DP is different from well-studied privacy notions. Central and user-level DP assume that people trust the server/other silos. On the other end of the spectrum, local DP assumes that people do not trust anyone at all (even their own silo). Sitting between central and local DP, ISRL-DP makes the realistic assumption (in cross-silo FL) that people trust their own silo, but not the server or other silos. In this work, we provide tight (up to logarithms) upper and lower bounds for ISRL-DP FL with convex/strongly convex loss functions and homogeneous (i.i.d.) silo data. Remarkably, we show that similar bounds are attainable for smooth losses with arbitrary heterogeneous silo data distributions, via an accelerated ISRL-DP algorithm. We also provide tight upper and lower bounds for ISRL-DP federated empirical risk minimization, and use acceleration to attain the optimal bounds in fewer rounds of communication than the state-of-the-art. Finally, with a secure "shuffler" to anonymize silo messages (but without a trusted server), our algorithm attains the optimal central DP rates under more practical trust assumptions. Numerical experiments show favorable privacy-accuracy tradeoffs for our algorithm in classification and regression tasks.
National University of Singapore（新加坡国立大学）；The University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）；Northeastern University（东北大学）
Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $ε$ on accu…
Renmin University of China（中国人民大学）；Kyoto University（京都大学）
Federated Learning (FL) is a promising machine learning paradigm that enables the analyzer to train a model without collecting users' raw data. To ensure users' privacy, differentially private federated learning has been intensively studied. The existing works are mainly based on the \textit{curator model} or \textit{local model} of differential privacy. However, both of them have pros and cons. The curator model allows greater accuracy but requires a trusted analyzer. In the local model where users randomize local data before sending them to the analyzer, a trusted analyzer is not required bu…
Sharif University of Technology（谢里夫理工大学）；Nokia Bell Labs（诺基亚贝尔实验室）
The emerging applications of machine learning algorithms on mobile devices motivate us to offload the computation tasks of training a model or deploying a trained one to the cloud or at the edge of the network. One of the major challenges in this setup is to guarantee the privacy of the client data. Various methods have been proposed to protect privacy in the literature. Those include (i) adding noise to the client data, which reduces the accuracy of the result, (ii) using secure multiparty computation (MPC), which requires significant communication among the computing nodes or with the client…
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
School of Electrical and Computer Engineering, National Technical University of Athens（电气与计算机工程学院，国家技术大学雅典）；Faculty of Sciences, University of Novi Sad（科学学院，诺维萨德大学）
Performing computations while maintaining privacy is an important problem in todays distributed machine learning solutions. Consider the following two set ups between a client and a server, where in setup i) the client has a public data vector $\mathbf{x}$, the server has a large private database of data vectors $\mathcal{B}$ and the client wants to find the inner products $\langle \mathbf{x,y_k} \rangle, \forall \mathbf{y_k} \in \mathcal{B}$. The client does not want the server to learn $\mathbf{x}$ while the server does not want the client to learn the records in its database. This is in con…
This paper introduces the problem of Private Linear Transformation (PLT) which generalizes the problems of private information retrieval and private linear computation. The PLT problem includes one or more remote server(s) storing (identical copies of) $K$ messages and a user who wants to compute $L$ independent linear combinations of a $D$-subset of messages. The objective of the user is to perform the computation by downloading minimum possible amount of information from the server(s), while protecting the identities of the $D$ messages required for the computation. In this work, we focus on…
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However, Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. This work presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides …
This paper considers the single-server Private Linear Transformation (PLT) problem with individual privacy guarantees. In this problem, there is a user that wishes to obtain $L$ independent linear combinations of a $D$-subset of messages belonging to a dataset of $K$ messages stored on a single server. The goal is to minimize the download cost while keeping the identity of each message required for the computation individually private. The individual privacy requirement ensures that the identity of each individual message required for the computation is kept private. This is in contrast to the…
The Gamer's Private Network (GPN) is a client/server technology created by WTFast for making the network performance of online games faster and more reliable. GPN s use middle-mile servers and proprietary algorithms to better connect online video-game players to their game's servers across a wide-area network. Online games are a massive entertainment market and network latency is a key aspect of a player's competitive edge. This market means many different approaches to network architecture are implemented by different competing companies and that those architectures are constantly evolving. E…
Dongguan University of Technology（东莞理工学院）；University of California, Irvine（加利福尼亚大学尔湾分校）；Augusta University（奥古斯塔大学）
This paper proposes Prism, a secret sharing based approach to compute private set operations (i.e., intersection and union), as well as aggregates over outsourced databases belonging to multiple owners. Prism enables data owners to pre-load the data onto non-colluding servers and exploits the additive and multiplicative properties of secret-shares to compute the above-listed operations in (at most) two rounds of communication between the servers (storing the secret-shares) and the querier, resulting in a very efficient implementation. Also, Prism does not require communication among the server…
