This presentation is part of the Works-in-Progress session, which aims to provide authors with early feedback to adjust on-going research. Manuscript titles are redacted until the work has been published.

Unmanned Aerial Vehicles (UAVs) are gaining popularity for distributed systems used for a variety of tasks, such as inspection of dangerous environments, surveillance, and pursuit of a target. These systems use distributed machine learning algorithms to cooperate towards achieving an objective and are prone to denial of service (DoS) and integrity attacks. In this paper, we integrate a messaging mechanism and a coordination algorithm based on stochastic gradient descent (SGD) in a multi-agent network for target pursuit resilient against such attacks. The network consists of agents sending messages containing local data and estimates and uses the SGD algorithm to optimize the global loss by aggregating state estimates from immediate neighbors. The network can suffer from a denial of service (DoS) attack to disrupt the ordering of messages or an integrity attack where one agent sends arbitrary estimates to neighbors to disrupt the convergence of normal agents towards an optimal state. The messaging mechanism uses Hashgraph, a distributed ledger technology, to guarantee a correct ordering of messages. The SGD algorithm uses a centerpoint-based aggregation for converging to a target in the presence of compromised agents. We evaluate the approach using scenarios of target pursuit for multi-UAV systems using simulations in Microsoft Air- Sim with PX4 flight controllers. The evaluation results demonstrate cases for which the multi-agent system under attack is resilient and converges to the approximate optimal state.

Nicholas Potteiger is a Ph.D. candidate in computer science at Vanderbilt University. His current research interests are towards the resilience of cooperative learning algorithms in multi-agent systems.