Protecting Intellectual Property in Additive Manufacturing Systems Against Optical Side-Channel Attacks

Abstract

Additive Manufacturing (AM), also known as 3D printing, is gaining popularity in industry sectors, such as aerospace, automobile, medicine, and construction. As the market value of the AM industry grows, the potential risk of cyberattacks on AM systems is increasing. One of the high value assets in AM systems is the intellectual property, which is basically the blueprint of a manufacturing process. In this lecture, we present an optical side-channel attack to extract intellectual property in AM systems via deep learning. We found that the deep neural network can successfully recover the path for an arbitrary printing process. By using data augmentation, the neural network can tolerate a certain level of variation in the position and angle of the camera as well as the lighting conditions. The neural network can intelligently perform interpolation and accurately recover the coordinates of an image that is not seen in the training dataset. To defend against the optical side-channel attack, we propose to use an optical projector to artificially inject carefully crafted optical noise onto the printing area. We found that existing noise generation algorithms can effortlessly defeat a naive attacker who is not aware of the existence of the injected noise. However, an advanced attacker who knows about the injected noise and incorporates images with injected noise in the training dataset can defeat all of the existing noise generation algorithms. To address this problem, we propose three novel noise generation algorithms, one of which can successfully defend against the advanced attacker.