Learning Trust Over Directed Graphs in the Presence of Adversaries
IEEE Transactions on Automatic Control · 2025-12 · 70 (12) · 7788-7801
DOI: 10.1109/tac.2025.3578424 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2025-12. Verfasst von Orhan Eren Akgün und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: NSF, Air Force Office of Scientific Research.
Abstract (Originalsprache)
We investigate the problem of learning the trustworthiness of agents in a directed graph, where agents receive stochastic trust information about their in-neighbors. We consider a setting where an unknown subset of agents may be malicious and disseminate misinformation about the trustworthiness of other agents. We present a learning protocol where agents determine their trusted neighborhoods based on the stochastic trust information they receive, and leverage the opinions of their trusted neighbors to assess the trustworthiness of other agents. We show that, under mild assumptions about the communication network, agents can learn the trustworthiness of other agents almost surely. In addition, we establish an expected geometric convergence rate of the algorithm based on the properties of the stochastic trust values and the communication graph. Finally, we present numerical studies demonstrating that our convergence results hold in practice across various network topologies and with different numbers of malicious agents in the network.
Förderung
- NSF
- Air Force Office of Scientific Research
Zitieren
APA
Akgün, O. E., Day, A. K., Nedić, A., & Gil, S. (2025). Learning Trust Over Directed Graphs in the Presence of Adversaries. IEEE Transactions on Automatic Control, 70(12), 7788-7801. https://doi.org/10.1109/tac.2025.3578424
Vancouver
Akgün OE, Day AK, Nedić A, Gil S. Learning Trust Over Directed Graphs in the Presence of Adversaries. IEEE Transactions on Automatic Control. 2025;70(12):7788-7801. doi:10.1109/tac.2025.3578424
BibTeX
@article{Akgn2025,
author = {Akgün, Orhan Eren and Day, Arif Kerem and Nedić, Angelia and Gil, Stephanie},
title = {Learning Trust Over Directed Graphs in the Presence of Adversaries},
journal = {IEEE Transactions on Automatic Control},
year = {2025},
volume = {70},
number = {12},
pages = {7788--7801},
doi = {10.1109/tac.2025.3578424}
}
EUVIMED