Location
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
Start Date
4-2-2026 1:30 PM
End Date
4-2-2026 3:30 PM
Presentation Date
April 2, 2026; 1:30pm-3:30pm
Description
Federated Learning (FL) leverages the intelligence of untrusted distributed devices through collaborative training. This makes the training process susceptible to malicious behavior. Existing defense mechanisms largely consider an adversary who attacks a proactive FL server without any adaptability. However, they overlook the presence of a strategic adversary. To address this challenge, our work proposes a Robust Game-theoretic framework where the adversary is both strategic and is equipped with the capability of performing large-scale poisoning attacks.
Biography
Manoj Twarakavi is a Ph.D. Student in the Department of Computer Science at Missouri University of Science and Technology, where he is advised by Professor Siddhardh Nadendla. His research focuses on Internet of Things, Machine Learning, Cybersecurity and Game Theory. Prior to joining Missouri S&T, Mr. Twarakavi earned a Master's degree in Computer Science from the University of Texas at Arlington and a Bachelor's degree in Computer Science and Engineering from M.S. Ramaiah Institute of Technology, India.
Meeting Name
2026 - Miners Solving for Tomorrow Research Conference
Department(s)
Computer Science
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2026 The Authors, All rights reserved
Included in
Robust Federated Learning with Strategic Adversaries
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
Federated Learning (FL) leverages the intelligence of untrusted distributed devices through collaborative training. This makes the training process susceptible to malicious behavior. Existing defense mechanisms largely consider an adversary who attacks a proactive FL server without any adaptability. However, they overlook the presence of a strategic adversary. To address this challenge, our work proposes a Robust Game-theoretic framework where the adversary is both strategic and is equipped with the capability of performing large-scale poisoning attacks.
Comments
Advisor: V. Sriram Siddhardh Nadendla, nadendla@mst.edu
"