THz-TDS for IC packaging material changes detection under real-world conditions

This study scrutinizes the limitations and challenges of applying non-destructive techniques such as Scanning Acoustic Microscopy (SAM) and 3D X-ray imaging for testing 3D and 2.5D integrated circuit (IC) packaging configurations. As the semiconductor industry moves towards advanced packaging technologies like 2.5D and 3D heterogeneous integration, which integrates various dies or chiplet components vertically and horizontally to enhance device performance and reduce costs, ensuring the reliability of these complex structures becomes paramount. This paper presents a comprehensive review of the current state-of-the-art non-destructive methods used for physical inspection, characterization, and failure analysis, with a focus on SAM and 3D X-ray imaging. It discusses the pressing challenges faced by these methods due to ongoing miniaturization and the need for high precision in inspecting densely packed components. An empirical investigation is conducted through a case study of a multi-die advanced packaging scenario to evaluate the practical utility of SAM and 3D X-ray techniques. This examination includes comparisons of resolution, analysis window size, aiming to understand the benefits of integrating these imaging modalities. The study also explores the future needs and opportunities for advancement in imaging hardware and algorithm development for automated signal interpretation and AI-assisted defect detection. This investigation highlights the critical role of non-destructive methods in advancing semiconductor packaging technologies while addressing their current limitations and the path forward for enhancing IC package integrity and reliability.

show abstract

SHIELD-PCB: securing hardware inspection with enhanced learning and defense against adversarial examples in printed circuit boards images

Ghosh,

Roy,

Varshney

et al. 2024

Applications of Machine Learning 2024

View full text Add to dashboard Cite

This study aims to investigate the potential of enhancing the resilience of computer vision systems in the context of intelligent Printed Circuit Board (PCB) inspection through the integration of techniques that filter out adversarial examples. PCBs, which are crucial components of electronic devices, require reliable inspection methods. However, current computer vision models are vulnerable to adversarial attacks that can compromise their accuracy. Our research introduces an evolving approach that combines advanced deep learning architectures with adversarial training methods. The initial steps involve training a robust PCB inspection model using a diverse dataset and generating adversarial examples through carefully designed perturbations. Subsequently, the model is exposed to these adversarial examples during a dedicated training phase, enabling it to adapt to variations introduced by potential adversaries. To counter the impact of adversarial examples on classification decisions during real-time inspections, a filtration mechanism is implemented to identify and discard them. Preliminary experimentation and ongoing evaluations demonstrate promising progress in enhancing the resilience of PCB inspection models against adversarial attacks. Although the filtration mechanism is still in its early stages, it shows potential in identifying and neutralizing potential threats, contributing to efforts aimed at strengthening the reliability and trustworthiness of inspection outcomes. Moreover, the adaptability of the proposed methodology to various PCB designs, including different components, orientations, and lighting conditions, indicates the potential for transformative advancements in computer vision systems in critical domains. This research underscores the need for continued investigation into the evolving landscape of adversarial example filtration, presenting a potential avenue for fortifying intelligent inspection systems against adversarial threats in PCB inspection and beyond.

show abstract

THz-TDS for IC packaging material changes detection under real-world conditions

Cited by 4 publications

References 36 publications

Evaluating a Multimodal, Non-Destructive Approach Combining a Resonant Cavity System and Infrared Spectroscopy to Detect Counterfeit and Anomalous Integrated Circuits

Evaluating a Multimodal, Non-Destructive Approach Combining a Resonant Cavity System and Infrared Spectroscopy to Detect Counterfeit and Anomalous Integrated Circuits

Challenges and opportunities in non-destructive characterization of stacked IC packaging: insights from SAM and 3D x-ray analysis

SHIELD-PCB: securing hardware inspection with enhanced learning and defense against adversarial examples in printed circuit boards images

Contact Info

Product

Resources

About