Publications

A method may include an aggregator node in a distributed computer network: generating an aggregator node public/private key pair; communicating the aggregator node public key to participant nodes; receiving, from each participant node, a message comprising a local machine learning (ML) model encrypted with a participant node private key and the aggregator node public key, and a participant node public key encrypted with the aggregator node public key; decrypting the local ML models and the participant node public keys using the aggregator node public key; decrypting the local ML models using the participant node public keys; generating an aggregated ML model based on the local ML models; encrypting, with each participant node public key, the aggregated ML model; and communicating the encrypted ML models to all participant nodes. Each participant node decrypts one of the encrypted ML models and modifies its local ML model with the aggregated ML model.

Conventional federated learning frameworks suffer from several challenges including performance bottlenecks at the central aggregation server, data bias, poor model convergence, and exposure to model poisoning attacks, and limited trust in the centralized infrastructure. In the current paper, a novel game theory-based approach called ‘pFedGame’ is proposed for decentralized federated learning, best suitable for temporally dynamic networks. The proposed algorithm works without any centralized server for aggregation and incorporates the problem of vanishing gradients and poor convergence over temporally dynamic topology among federated learning participants. The solution comprises two sequential steps in every federated learning round, for every participant. First, it selects suitable peers for collaboration in federated learning. Secondly, it executes a two-player constant sum cooperative game to reach convergence by applying an optimal federated learning aggregation strategy. Experiments performed to assess the performance of pFedGame in comparison to existing methods in decentralized federated learning have shown promising results with accuracy higher than 70% for heterogeneous data.

A method for privacy preserving machine learning model sharing may include a computer program for a first institution of a plurality of institutions in a distributed ledger network: receiving transaction data for a transaction; training a local machine learning model using the transaction data; submitting parameters for the local machine learning model to the distributed ledger network as a private transaction with a trusted entity, wherein the trusted entity receives parameters for a plurality of local machine learning models from the distributed ledger network for the plurality of institutions in the distributed ledger network and aggregates the parameters into an aggregated machine learning model and submits the aggregated parameters to the distributed ledger network as one or more transactions; receiving, from the distributed ledger network, the aggregated parameters for the aggregated machine learning model; and updating the local machine learning model with the aggregated parameters.

Systems and methods for generating synthetic data using federated, collaborative, privacy preserving learning models are disclosed. In one embodiment, a method for generating synthetic data from real data for use in a federated learning network may include: (1) conducting, by a backend for a first institution of a plurality of institutions in a federated learning network, a transaction comprising transaction data; (2) generating, by the backend for the first institution, local synthetic data for the transaction data using a local synthetic data generating model; (3) sharing, by the backend for the first institution, the local synthetic data with a plurality of backends for other institutions; (4) receiving, by the backend for the first institution, global synthetic data from the plurality of backends for the other institutions; and (5) training, by the backend for the first institution, a local machine learning model with the global synthetic data.

Systems and methods for federated learning based on a reward-driven approach are disclosed. In one embodiment, a method may include: (1) receiving, by a federated contribution computer program executed by a federated node in a distributed ledger network, a plurality of local machine learning model updates from a plurality of clients in the distributed ledger networks; (2) retrieving, by the federated contribution computer program, a prior global machine learning model; (3) calculating, by the federated contribution computer program, a current global machine learning model based on the prior global machine learning model and the plurality of local machine learning model updates; (4) determining, by the federated contribution computer program, a federated contribution for each client based on each client's federated contribution to the current global machine learning model; and (5) issuing, by the federated contribution computer program, rewards to each client based on the client's federated contribution.

This article describes experimental research studies conducted toward understanding the implementation aspects of high-capacity quantum-secured optical channels in mission-critical metro-scale operational environments using quantum key distribution (QKD) technology. To the best of our knowledge, this is the first time that an 800 Gbps quantum-secured optical channel—along with several other dense wavelength division multiplexed channels on the C-band and multiplexed with the QKD channel on the O-band-was established at distances up to 100 km, with secret key-rates relevant for practical industry use cases. In addition, during the course of these trials, transporting a blockchain application over this established channel was utilized as a demonstration of securing a financial transaction in transit over a quantum-secured optical channel. The findings of this research pave the way toward the deployment of QKD-secured optical channels in high-capacity, metro-scale, mission-critical operational environments, such as Inter-Data Center Interconnects.

As Deep Learning algorithms continue to evolve and become more sophisticated, they require massive datasets for model training and efficacy of models. Some of those data requirements can be met with the help of existing datasets within the organizations. Current Machine Learning practices can be leveraged to generate synthetic data from an existing dataset. Further, it is well established that diversity in generated synthetic data relies on (and is perhaps limited by) statistical properties of available dataset within a single organization or entity. The more diverse an existing dataset is, the more expressive and generic synthetic data can be. However, given the scarcity of underlying data, it is challenging to collate big data in one organization. The diverse, non-overlapping dataset across distinct organizations provides an opportunity for them to contribute their limited distinct data to a larger pool that can be leveraged to further synthesize. Unfortunately, this raises data privacy concerns that some institutions may not be comfortable with. This paper proposes a novel approach to generate synthetic data - FedSyn. FedSyn is a collaborative, privacy preserving approach to generate synthetic data among multiple participants in a federated and collaborative network. FedSyn creates a synthetic data generation model, which can generate synthetic data consisting of statistical distribution of almost all the participants in the network. FedSyn does not require access to the data of an individual participant, hence protecting the privacy of participant's data. The proposed technique in this paper leverages federated machine learning and generative adversarial network (GAN) as neural network architecture for synthetic data generation. The proposed method can be extended to many machine learning problem classes in finance, health, governance, technology and many more.

Systems and methods for federated learning using peer-to-peer networks are disclosed. A method may include: electing a participant node as a collaborator node using a consensus algorithm; the collaborator node generating and broadcasting a public/private key pair; the participant nodes generating public/private key pairs for each communication with the collaborator node, encrypting and broadcasting a message comprising a parameter for a local machine learning model for the participant node and its public key with the collaborator node's public key, the collaborator node decrypting the encrypted messages, updating an aggregated machine learning model with the decrypted parameters, encrypting and broadcasting update messages each comprising an update with each participant node's public key; the participant nodes decrypting one of the messages with their private keys, and the participant nodes updating their local machine learning models with the update.

In recent times, Machine learning and Artificial intelligence have become one of the key emerging fields of computer science. Many researchers and businesses are benefited by machine learning models that are trained by data processing at scale. However, machine learning, and particularly Deep Learning requires large amounts of data, that in several instances are proprietary and confidential to many businesses. In order to respect individual organization’s privacy in collaborative machine learning, federated learning could play a crucial role. Such implementations of privacy preserving federated learning find applicability in various ecosystems like finance, health care, legal, research and other fields that require preservation of privacy. However, many such implementations are driven by a centralized architecture in the network, where the aggregator node becomes the single point of failure, and is also expected with lots of computing resources at its disposal. In this paper, we propose an approach of implementing a decentralized, peer-topeer federated learning framework, that leverages RAFT based aggregator selection. The proposal hinges on that fact that there is no one permanent aggregator, but instead a transient, time based elected leader, which will aggregate the models from all the peers in the network. The leader ( aggregator) publishes the aggregated model on the network, for everyone to consume. Along with peer-to-peer network and RAFT based aggregator selection, the framework uses dynamic generation of cryptographic keys, to create a more secure mechanism for delivery of models within the network. The key rotation also ensures anonymity of the sender on the network too. Experiments conducted in the paper, verifies the usage of peer-to-peer network for creating a resilient federated learning network. Although the proposed solution uses an artificial neural network in it’s reference implementation, the generic design of the framework can accommodate any federated learning model within the network.

Over the recent years, Federated machine learning continues to gain interest and momentum where there is a need to draw insights from data while preserving the data provider's privacy. However, one among other existing challenges in the adoption of federated learning has been the lack of fair, transparent and universally agreed incentivization schemes for rewarding the federated learning contributors. Smart contracts on a blockchain network provide transparent, immutable and independently verifiable proofs by all participants of the network. We leverage this open and transparent nature of smart contracts on a blockchain to define incentivization rules for the contributors, which is based on a novel scalar quantity - federated contribution. Such a smart contract based reward-driven model has the potential to revolutionize the federated learning adoption in enterprises. Our contribution is two-fold: first is to show how smart contract based blockchain can be a very natural communication channel for federated learning. Second, leveraging this infrastructure, we can show how an intuitive measure of each agents' contribution can be built and integrated with the life cycle of the training and reward process.

Federated learning has become one of the most recent and widely researched areas of machine learning. Several machine-learning frameworks, such as Tensorflow Federated and PySyft and others have gained momentum in recent past and continue to evolve. Some of the frameworks involve techniques such as differential privacy, secure multi-party computation, gradient descent calculation over the network to achieve privacy of underlying data in federated learning. While these frameworks serve the need for a general-purpose federated learning model as per certain framework, in this paper we present a solution based on distributed messaging with appropriate entitlements that enterprises can leverage in a managed and permissioned network. The solution implements access controls on message source and destination in a decentralized network, which can implement any given data science model in the federated network to facilitate secure federated learning.