Cybenko has served as an advisor for the Defense Science Board and several other government panels and is the founding editor-in-chief of the IEEE Security & Privacy magazine. His current research interests are distributed information, control systems, and signal processing, with a focus on applications to security and infrastructure protection. He is known for proving the universal approximation theorem for artificial neural networks with sigmoid activation functions.
- Princeton EE alumni profiles
- Cybenko, G. (1989) "Approximations by superpositions of sigmoidal functions", Mathematics of Control, Signals, and Systems, 2(4), 303–314. doi:10.1007/BF02551274