Objective: The learning objective of this module is for trainees to gain hand experiences on IC level Hardware Trojan Detection by using nano-image analysis and artificial intelligence. Trainees will learn step by step, how to use physical inspection methods such as scanning electron microscopy (SEM) to detect any malicious changes from the backside of an IC. Hardware Trojans are malicious changes to the design of integrated circuits (ICs) at different stages of the design and fabrication processes. Advanced computer vision algorithms in combination with the neural network models are used to classify authentic and malicious cells from an IC under authentication by assigning as a unique descriptor for each type of logic cells/gates. These descriptors are compared with a golden standard to detect any subtle changes on the active region, which can raise the flag for the existence of a potential hardware Trojan.
Target Audience: Government officers, Scientists
Prerequisite Knowledge and Skills:
- programming knowledge: python
- Xilinx FPGA
Resources Provided at the Training | Deliverables:
- Detailed description of set-ups used in training
- A video demo of the module
Learning Outcome: This work has been done to detect malicious changes by an untrusted foundry inside an IC using Xilinx FPGA. After successfully finishing this experiment, a trainee will learn understand, what can be a hardware Trojan, Sample Preparation Process, various SEM imaging modalities. Also, how to use image analysis and artificial intelligence methods for hardware assurance.