Report Title: Jamming Attacks on Decentralized Federated Learning in Multi-Hop Wireless Networks

Presenter: Associate Professor Shi Yi

Affiliation: Virginia Tech, USA

Report Time: August 16 (Wednesday) 14:30-15:30

Report Location: Jade Science and Education Building A, Room 1602

Report Abstract: A wireless sensor network is deployed to monitor signal transmissions of interest across a large area. Each sensor receives signals under specific channel conditions based on its location and trains an individual deep neural network model for signal classification. To enhance accuracy, the network utilizes decentralized federated learning over a multi-hop wireless network, allowing collective training of a deep neural network for signal identification. In this approach, sensors broadcast their trained models to neighboring sensors, gather models from neighbors, and aggregate them to initialize their own models for the next round of training. This iterative process builds a common deep neural network across the network while preserving the privacy of signals collected at different locations. Evaluations are conducted to assess signal classification accuracy, convergence time, communication overhead reduction, and energy consumption in various network topologies and packet loss scenarios. The impact of random sensor participation in model updates is also considered. Additionally, we investigate an effective attack strategy that employs jammers to disrupt model exchanges between nodes. Two attack scenarios are examined: First, the adversary can attack any link within a given budget, rendering the two end nodes unable to exchange their models. Second, jammers with limited jamming ranges are deployed, and each jammer can only disrupt nodes within its range. When a directional link is attacked, the receiver node cannot receive the model from the transmitter node. We develop algorithms to select links to be attacked in both scenarios and design algorithms to deploy jammers optimally, maximizing their impact on the decentralized federated learning process. We evaluate these algorithms using wireless signal classification as the use case over a large network area, exploring how these attack mechanisms exploit various aspects of learning, connectivity, and sensing.

Personal Introduction: Shi Yi, Ph.D., is currently an associate professor at Virginia Tech, USA, and was formerly the chief researcher at Intelligent Automation Inc. in the USA. Associate Professor Shi Yi is a renowned expert in the field of AI security and optimization. He has published over 180 papers in prestigious international journals and conferences, with over 20 papers being cited more than 100 times each, and the highest single citation exceeding 800. Associate Professor Shi Yi has twice won the Best Paper Award at the renowned wireless network conference INFOCOM in 2008 and 2011, and received the IEEE INFOCOM Test of Time Award in 2023. He also won the Best Student Paper Award at ACM WUWNet 2014 and the Best Paper Award at IEEE HST 2018. Associate Professor Shi Yi has served as the technical committee chair for multiple IEEE and ACM Symposiums, Tracks, Workshops, and as an editor for IEEE Communications Surveys and Tutorials and IEEE Transactions on Cognitive Communications and Networking.