Interactive Simulations of Backdoors in Neural Networks

TL;DR

This paper introduces an interactive web-based platform for simulating the planting, activation, and defense of cryptographic backdoors in neural networks, aiding understanding and development of secure AI models.

Contribution

It presents a novel simulation playground that models cryptographic backdoor scenarios in neural networks, facilitating research on backdoor planting and defense strategies.

Findings

Simulation of backdoor planting in extended neural network architectures.

Defense mechanisms based on proximity analysis demonstrated.

Platform enables interactive exploration of backdoor vulnerabilities.

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: in the extension of NN model architecture to support digital signature verification and in the modified architectural block for non-linear operators. Simulations of backdoor defense against backdoors are available based on proximity analysis and provide a playground for a game of planting and defending against backdoors. The simulations are available at https://pages.nist.gov/nn-calculator