First Auto-Magnifier Platform for Hardware Assurance and Reverse Engineering Integrated Circuits

Scanning Electron Microscopy (SEM) is a common imaging modality used in the semiconductor industry particularly for failure analysis In addition, with the recent growing concern of physical attacks on electronics with malicious intent, SEMs are becoming more attractive for hardware assurance and especially, Reverse Engineering (RE) However, RE requires long hours of imaging for an IC even if it is done automatically. In With the ongoing trend of adding more structures onto a limited space on the IC, the imaging time frame is becoming unfeasible. This drawback would be manageable in situations where there is a prior knowledge on the exact location to be imaged. However, in case of hardware assurance and reverse engineering, where all the structures in the entire IC need to be extracted precisely without any prior knowledge, the drawback would be a major limiting factor. There are several parameters in the SEM imaging modality such as magnification that can be adjusted to reduce the time requirements. In [4], Principe et al. even introduced a platform for automated processing for an IC. However, both approaches do not consider the density of the structures being imaged and fails to investigate if the region warrants a high definition setting to resolve the features satisfactorily. In this paper, we introduce a new algorithm that can quantify the density of objects in a region using a fast-acquired low magnification image and define the right value of magnification for imaging different regions automatically. Once the density of the objects is quantified the microscope can increase the magnification with a predefined step (10X, 100X, 1000X, etc.) and collect new images but only from the region detected as a dense region. This loop will be repeated until the whole area is imaged with the right magnification. The images are assumed to be analyzed using advanced image analysis methods incorporated with machine learning and deep learning algorithms for hardware assurance. Therefore, as the image analysis algorithms are further developed a lower magnified image might be also acceptable for analysis. This will be used towards building an intelligent microscope that can considerably reduce the imaging time requirement which would greatly facilitate efficient hardware assurance and RE.