Interactive Simulations of Backdoors in Neural Networks

Abstract

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable backdoors under theoretical assumptions in the large AI model systems deployed in practice. Our approach is based on designing a web-based simulation playground that enables planting, activating, and defending cryptographic backdoors in neural networks (NN). Simulations of planting and activating backdoors are enabled for two scenarios: (a) in the extension of the NN model architecture to support digital signature verification, and (b) in the modified architectural block for non-linear operators. Simulations of backdoor defense against backdoors are available based on proximity analysis and provide an educational tool and a playground for a game of planting and defending against backdoors.