Invited paper: *Lack of Quorum Sensing Leads to Failure of Consensus in Temnothorax Ant Emigration.

SSS 2021 is the 23rd International Symposium on Stabilization, Safety, and Security of Distributed Systems.

This is Jiajia’s first theoretical work.

*Invited paper is the prestigious form of publication at SSS 2021. 

CCAC 2021: 5th IEEE Columbian conference on Automatic Control

Workshop: 

Resilient distributed machine learning: Secure multi-agent federation [Slides]

Abstract: 

With the rapid increasing data-collection, storage, and computation capabilities of personal computing devices such as laptops and smartphones, and with the growing popularity of wearable devices such as Apple Watch, one recent trend in machine learning is to outsource part of the involved computation burden to external edge and/or end devices; in a sense, the edge and end devices can be viewed as external workers of the cloud.

In this workshop, we will introduce Federated Learning – a practical learning paradigm wherein the training data is kept confidentially on users’ own end devices. Then we will talk about the vulnerabilities of FL to different types of internal and external failures and attacks — formal and rigorous mathematical models will be provided. We will talk about several state-of-the-art approaches to tackle this variety of vulnerabilities, starting from the relatively simple distributed context awareness problems to the more advanced Byzantine-resilient regression problems. Specifically, we will talk about how to be able to handle the local data sparsity, measurement contamination, arbitrarily malicious misleading messages, adversary collusion, etc.