IEEE Princeton Central Jersey Section

This is a weekly session of the CIT Summer Series, with David A Fisher presenting Why Software Fails and Why AI cannot Help : It was once widely believed that computers would enhance the speed, reliability, and applicability of human deductive reasoning in the physical and social sciences, much as motorized vehicles (e.g., cars, trains, airplanes) have enhanced the speed, reliability, and applicability of human manual abilities in transportation. Yet, 60 years later, computers can be used confidently only for paperwork tasks, analysis of regularly structured data, and simple process control applications. Complex software rarely satisfies user needs, is untrustworthy and difficult to maintain, and largely opaque to its users. Artificial intelligence (AI) methods including heuristics, machine learning, and statistical methods are in opposition to sound deductive reasoning. This presentation explains certain practical and logical impediments to computer enhancement of human deductive reasoning, the deductive limitations of modern programming languages, the role of AI, and provides some promising alternatives. Speaker(s): David A Fisher, Virtual: https://events.vtools.ieee.org/m/364005

This is a weekly session of the CIT Summer Series, with David A. Bader presenting Solving Global Grand Challenges with High Performance Data Analytics : Data science aims to solve grand global challenges such as: detecting and preventing disease in human populations; revealing community structure in large social networks; protecting our elections from cyber-threats, and improving the resilience of the electric power grid. Unlike traditional applications in computational science and engineering, solving these social problems at scale often raises new challenges because of the sparsity and lack of locality in the data, the need for research on scalable algorithms and architectures, and development of frameworks for solving these real-world problems on high performance computers, and for improved models that capture the noise and bias inherent in the torrential data streams. In this talk, Bader will discuss the opportunities and challenges in massive data science for applications in social sciences, physical sciences, and engineering. Speaker(s): David A Bader, Virtual: https://events.vtools.ieee.org/m/364003

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