Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning

By Muhammad Shayan, Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh. 2018

88 citations recorded by the source corpus.

Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must trust that the central service does not use the byproducts of client data. In addition to this, a group of malicious clients could also harm the performance of the model by carrying out a poisoning attack. As a response, we propose Biscotti: a fully decentralized peer to peer (P2P) approach to multi-party ML, which uses blockchain and cryptographic primitives to coordinate a privacy-preserving ML process between peering clients. Our evaluation demonstrates that Biscotti is scalable, fault tolerant, and defends against known attacks. For example, Biscotti is able to protect the privacy of an individual client's update and the performance of the global model at scale when 30% of adversaries are trying to poison the model. The implementation can be found at: this https URL

Subfields: Artificial Intelligence, Federated & Distributed Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Federated & Distributed Learning

In Privacy & Security

Citations in the corpus

How To Backdoor Federated Learning (2018, background): “models [18, 59, 60], or require participants to submit their data for centralized training [27].”
Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach (2019, background): “However, the most existing work made an optimistic assumption that all the mobile devices will unconditionally participate in federated learning when invited [8], [9], which is not practical in the real world due to resource costs incurred by model training [10].”
Reliable Federated Learning for Mobile Networks (2019, methodology): “The workers obtain rewards from the task publisher according to their data contribution and model training behaviors for the federated learning task [5], [13].”
Federated Learning for Healthcare Informatics (2019, background): “Therefore, some researches began to study fully decentralized framework where the central server is not required [41, 60, 85, 91].”
Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices (2019, methodology): “In our experiment, we distribute the MNIST data set [52] with 60 000 images to ten participants equally so that each participant (i.e., each device) has 6000 images.”
Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, unknown): “After a model is trained, the performance of the local device is evaluated, using the Reject on Negative Impact (RONI) [148] method for Independent and Identically Distribute (IID) data.”
A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, methodology): “[112] proposed Biscotti, a P2P learning method with a blockchain ledger.”
Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract Theory (2019, methodology): “, reject on negative influence (RONI) scheme in [4] for independent and identically distributed (IID) data scenarios and FoolsGold scheme in [19] for non-IID data scenarios, to identify the poisoning attacks and unreliable workers (step 1 in Fig.”