An Overview of Laser Injection against Embedded Neural Network Models

TL;DR

This paper discusses how laser injection attacks pose significant security threats to embedded neural network models in IoT devices, emphasizing the need for combined efforts from AI and physical security communities.

Contribution

It highlights the risks of laser injection attacks on embedded neural networks and advocates for interdisciplinary collaboration to address these vulnerabilities.

Findings

Laser injection can precisely target embedded neural networks.

Such physical attacks threaten the integrity and confidentiality of AI models.

The paper calls for joint efforts between AI and security fields.

Abstract

For many IoT domains, Machine Learning and more particularly Deep Learning brings very efficient solutions to handle complex data and perform challenging and mostly critical tasks. However, the deployment of models in a large variety of devices faces several obstacles related to trust and security. The latest is particularly critical since the demonstrations of severe flaws impacting the integrity, confidentiality and accessibility of neural network models. However, the attack surface of such embedded systems cannot be reduced to abstract flaws but must encompass the physical threats related to the implementation of these models within hardware platforms (e.g., 32-bit microcontrollers). Among physical attacks, Fault Injection Analysis (FIA) are known to be very powerful with a large spectrum of attack vectors. Most importantly, highly focused FIA techniques such as laser beam injection enable very accurate evaluation of the vulnerabilities as well as the robustness of embedded systems. Here, we propose to discuss how laser injection with state-of-the-art equipment, combined with theoretical evidences from Adversarial Machine Learning, highlights worrying threats against the integrity of deep learning inference and claims that join efforts from the theoretical AI and Physical Security communities are a urgent need.