Related papers: Human-machine Hierarchical Networks for Decision M…
In this paper, we study a fully-decentralized multi-agent policy evaluation problem, which is an important sub-problem in cooperative multi-agent reinforcement learning, in the presence of up to $f$ faulty agents. In particular, we focus on…
Recent Byzantine fault-tolerant (BFT) state machine replication (SMR) protocols increasingly focus on scalability to meet the requirements of distributed ledger technology (DLT). Validating the performance of scalable BFT protocol…
\textit{When an adversary gets access to the data sample in the adversarial robustness models and can make data-dependent changes, how has the decision maker consequently, relying deeply upon the adversarially-modified data, to make…
We study resilient quantized consensus in multi-agent systems, where some agents may malfunction. The network consists of agents taking integer-valued states, and the agents' communication is subject to asynchronous updates and time delays.…
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…
Recently, a novel peer sampling protocol, Elevator, was introduced to construct network topologies tailored for emerging decentralized applications such as federated learning and blockchain. Elevator builds hub-based topologies in a fully…
This paper considers the problem of Byzantine fault-tolerance in multi-agent decentralized optimization. In this problem, each agent has a local cost function. The goal of a decentralized optimization algorithm is to allow the agents to…
Blockchain systems benefit from lessons in prior art such as fault tolerance, distributed systems, peer-to-peer systems, and game theory. In this paper we argue that blockchain algorithms should tolerate both rational (self-interested)…
Decision making in large scale urban environments is critical for many applications involving continuous distribution of resources and utilization of infrastructure, such as ambient lighting control and traffic management. Traditional…
One of the most celebrated problems of fault-tolerant distributed computing is the consensus problem. It was shown to abstract a myriad of problems in which processes have to agree on a single value. Consensus applications include…
This work seeks to design decisionmaking rules for autonomous agents to jointly influence and optimize the behavior of teamed human decisionmakers in the presence of an adversary. We study a situation in which computational jobs are…
We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being…
Federated learning has arisen as a mechanism to allow multiple participants to collaboratively train a model without sharing their data. In these settings, participants (workers) may not trust each other fully; for instance, a set of…
This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of…
In Byzantine collaborative learning, $n$ clients in a peer-to-peer network collectively learn a model without sharing their data by exchanging and aggregating stochastic gradient estimates. Byzantine clients can prevent others from…
Numerous distributed applications, such as cloud computing and distributed ledgers, necessitate the system to invoke asynchronous consensus objects an unbounded number of times, where the completion of one consensus instance is followed by…
Self-stabilization is an versatile approach to fault-tolerance since it permits a distributed system to recover from any transient fault that arbitrarily corrupts the contents of all memories in the system. Byzantine tolerance is an…
To defend against Byzantine attacks in decentralized learning, most existing methods rely on robust aggregation rules to mitigate the influence of malicious machines. However, these strategies inherently introduce bias, leading to inexact…
Automated decision systems increasingly rely on human oversight to ensure accuracy in uncertain cases. This paper presents a practical framework for optimizing such human-in-the-loop classification systems using a double-threshold policy.…
Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing devices/machines due to either design constraints…