Advanced packaging of microelectronic products, especially 3D integration and hybrid bonding, provide challenges to process control and physical failure analysis as well as for the understanding of failure mechanisms. In this talk, the inherent advantages of non-destructive X-ray computed tomography (XCT) in the sub-micron and nano range are demonstrated for fault isolation and for the understanding of the evolution of reliability-limiting defects in packaged microchips. Sub-micron and nano-XCT enable the representation of structures and defects (e.g. micropores and microcracks) in advanced packaging and interconnect structures. Another unique advantage of XCT — as opposed to destructive FA methods — is that kinetic processes such as crack propagation, which can lead to degradation and ultimately failure of microelectronic components, can be imaged with high resolution. Speaker(s): Ehrenfried Zschech, Virtual: https://events.vtools.ieee.org/m/363155

This is a weekly session of the CIT Summer Series, with Nael Abu-Ghazaleh presenting Security challenges and opportunities at the Intersection of Architecture and ML/AI : Machine learning is an increasingly important computational workload as data-driven deep learning models are becoming increasingly important in a wide range of application spaces. Computer systems, from the architecture up, have been impacted by ML in two primary directions: (1) ML is an increasingly important computing workload, with new accelerators and systems targeted to support both training and inference at scale; and (2) ML supporting architecture decisions, with new machine learning based algorithms controlling systems to optimize their performance, reliability and robustness. In this talk, I will explore the intersection of security, ML and architecture, identifying both security challenges and opportunities. Machine learning systems are vulnerable to new attacks including adversarial attacks crafted to fool a classifier to the attacker’s advantage, membership inference attacks attempting to compromise the privacy of the training data, and model extraction attacks seeking to recover the hyperparameters of a (secret) model. Architecture can be a target of these attacks when supporting ML, but also provides an opportunity to develop defenses against them, which I will illustrate with three examples from our recent work. First, I show how ML based hardware malware detectors can be attacked with adversarial perturbations to the Malware and how we can develop detectors that resist these attacks. Second, I will also show an example of a microarchitectural side channel attacks that can be used to extract the secret parameters of a neural network and potential defenses against it. Finally, I will also discuss how architecture can be used to make ML more robust against adversarial and membership inference attacks using the idea of approximate computing. I will conclude with describing some other potential open problems. Speaker(s): Nael Abu-Ghazaleh, Virtual: https://events.vtools.ieee.org/m/364001