Jamming Attacks on Decentralized Federated Learning in General Multi-Hop Wireless Networks

by   Yi Shi, et al.

Decentralized federated learning (DFL) is an effective approach to train a deep learning model at multiple nodes over a multi-hop network, without the need of a server having direct connections to all nodes. In general, as long as nodes are connected potentially via multiple hops, the DFL process will eventually allow each node to experience the effects of models from all other nodes via either direct connections or multi-hop paths, and thus is able to train a high-fidelity model at each node. We consider an effective attack that uses jammers to prevent the model exchanges between nodes. There are two attack scenarios. First, the adversary can attack any link under a certain budget. Once attacked, two end nodes of a link cannot exchange their models. Secondly, some jammers with limited jamming ranges are deployed in the network and a jammer can only jam nodes within its jamming range. Once a directional link is attacked, the receiver node cannot receive the model from the transmitter node. We design algorithms to select links to be attacked for both scenarios. For the second scenario, we also design algorithms to deploy jammers at optimal locations so that they can attack critical nodes and achieve the highest impact on the DFL process. We evaluate these algorithms by using wireless signal classification over a large network area as the use case and identify how these attack mechanisms exploits various learning, connectivity, and sensing aspects. We show that the DFL performance can be significantly reduced by jamming attacks launched in a wireless network and characterize the attack surface as a vulnerability study before the safe deployment of DFL over wireless networks.


Jamming Attacks on Federated Learning in Wireless Networks

Federated learning (FL) offers a decentralized learning environment so t...

Age of Information in Multihop Multicast Networks

We consider the age of information in a multihop multicast network where...

Detection and Prevention Against RTS Attacks in Wireless LAN

Widely deployed wireless network devices use a shared medium to communic...

Energy and Social Cost Minimization for Data Dissemination in Wireless Networks: Centralized and Decentralized Approaches

We study multi-hop data-dissemination in a wireless network from one sou...

Sniffing Multi-hop Multi-channel Wireless Sensor Networks

As wireless sensor networks grow larger, more complex and their role mor...

A Game-Theoretic and Experimental Analysis of Energy-Depleting Underwater Jamming Attacks

Security aspects in underwater wireless networks have not been widely in...

KPsec: Secure End-to-End Communications for Multi-Hop Wireless Networks

The security of cyber-physical systems, from self-driving cars to medica...

Please sign up or login with your details

Forgot password? Click here to reset