SAMSEM -- A Generic and Scalable Approach for IC Metal Line Segmentation

2026-03-17

AI Summary

This work addresses the challenge of detecting malicious circuits in integrated circuits (ICs) fabricated in untrusted environments, where accurate segmentation of metal interconnects in scanning electron microscopy (SEM) images is critical yet hindered by poor generalization across varying fabrication processes, materials, and imaging conditions. To overcome this, we present the first adaptation of Meta’s Segment Anything Model 2 (SAM2) to IC metal wire segmentation, introducing a unified framework that integrates multi-scale image processing and a topology-aware loss function prioritizing electrical connectivity over mere pixel-level accuracy. Extensive evaluation across 48 metal layers from 14 distinct ICs demonstrates that our approach achieves a low error rate of 0.72% on seen ICs and 5.53% on unseen ICs; with full fine-tuning, the overall error further drops to 0.62%, substantially enhancing cross-process and cross-chip generalization.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

In light of globalized hardware supply chains, the assurance of hardware components has gained significant interest, particularly in cryptographic applications and high-stakes scenarios. Identifying metal lines on scanning electron microscope (SEM) images of integrated circuits (ICs) is one essential step in verifying the absence of malicious circuitry in chips manufactured in untrusted environments. Due to varying manufacturing processes and technologies, such verification usually requires tuning parameters and algorithms for each target IC. Often, a machine learning model trained on images of one IC fails to accurately detect metal lines on other ICs. To address this challenge, we create SAMSEM by adapting Meta's Segment Anything Model 2 (SAM2) to the domain of IC metal line segmentation. Specifically, we develop a multi-scale segmentation approach that can handle SEM images of varying sizes, resolutions, and magnifications. Furthermore, we deploy a topology-based loss alongside pixel-based losses to focus our segmentation on electrical connectivity rather than pixel-level accuracy. Based on a hyperparameter optimization, we then fine-tune the SAM2 model to obtain a model that generalizes across different technology nodes, manufacturing materials, sample preparation methods, and SEM imaging technologies. To this end, we leverage an unprecedented dataset of SEM images obtained from 48 metal layers across 14 different ICs. When fine-tuned on seven ICs, SAMSEM achieves an error rate as low as 0.72% when evaluated on other images from the same ICs. For the remaining seven unseen ICs, it still achieves error rates as low as 5.53%. Finally, when fine-tuned on all 14 ICs, we observe an error rate of 0.62%. Hence, SAMSEM proves to be a reliable tool that significantly advances the frontier in metal line segmentation, a key challenge in post-manufacturing IC verification.

Problem

• IC metal line segmentation
• hardware assurance
• SEM image analysis
• cross-technology generalization
• post-manufacturing verification

Innovation

• SAM2 adaptation
• multi-scale segmentation
• topology-based loss
• cross-technology generalization
• IC metal line segmentation