[Seminar] Cryptography, Cyber Security and Machine Learning: Interdisciplinary benefits by Dr. Najwa Aaraj (TII)
Date
Location
Description
Abstract
Cyber Security and machine learning have typically been separate disciplines. Moreover, Cryptography and machine learning have typically been separate disciplines. New cross-discipline research is needed to improve the three domains
In this talk, we discuss how machine learning can be used as an enabler to advanced cryptography, privacy preserving protocols and cryptanalysis. We also discuss how efficient machine learning models can enable local inference and advanced vulnerability management on edge devices. The talk also covers how Neural Network algorithms and cryptographic cores will co-exist in future Neural Processor Units.
We cover the role of cryptography in securing Machine Learning models by (1) ensuring confidentiality of both data & model during training and classification; (2) protection of models from being tampered-with or introducing bias for profit or control; (3) protection against model poisoning; and (4) introducing cryptographic randomness in training Deep Neural Networks. This could help drive the adoption of AI in privacy-sensitive industries, including medicine and finance.
Speaker
Dr Najwa Aaraj is Chief Researcher at the Cryptography Research Center at Technology Innovation Institute (TII) and leads the research and development of post-quantum cryptography (PQC) software libraries and hardware implementations, lightweight cryptographic libraries for embedded and RF systems, cryptanalysis, quantum random number generation, and applied machine learning for cryptographic technologies. She is also Acting Chief Researcher at TII’s Autonomous Robotics Research Center, which is dedicated to breakthrough developments in robotics and autonomy.
She brings to her roles over 18 years of experience in applied cryptography, trusted platforms, security architecture for embedded systems, software exploit detection and prevention systems, and biometrics. She has been associated with global firms in multiple geographies from Australia to the United States.
Prior to joining TII, Dr Aaraj was Senior Vice President of Products & Cryptography Development at DarkMatter, a cyber-security leader based in the UAE. She was formerly at Booz & Company, where she led consulting engagements in the communication and technology industry for clients globally. She also assumed research positions within IBM T.J. Watson Security Research in New York State, and Intel Security Research Group in Portland, Oregon, where she worked on Trusted Platform Modules and contributed to an early prototype of a TPM 2.0 based firmware.
Dr Aaraj has authored multiple conference papers, Institute of Electrical and Electronics Engineers (IEEE) and Association for Computing Machinery (ACM) journal papers, books and book chapters, and received patents on applied cryptography, embedded system security, and machine learning-based protection of Internet of Things (IoT) systems.
Dr Aaraj is on the advisory board of New York-based Neutigers, a leading-edge startup revolutionising the next generation of energy/latency-efficient artificial intelligence (AI). She is also Adviser within the Strategic Advisory Group at Paladin Capital Group (Cyber Venture Capital) and Adjunct Professor at the Mohamed Bin Zayed University of Artificial Intelligence (Machine Learning Research Group). In addition, she is an Adviser to multiple security and Machine Learning startups including Okinawa Institute of Science and Technology Graduate University.
She received a Special Recognition award at the Arab Woman Awards 2021, held in partnership with the United Nations to recognise the notable achievements of the region’s women.
Dr Najwa Aaraj holds a PhD with Highest Distinction in Applied Cryptography and Embedded Systems Security from Princeton University (USA).
Zoom Link: https://oist.zoom.us/j/92621326004?pwd=bG5TRTlhNEdROVVVUUx1YjR3ay9JZz09
(Meeting ID: 926 2132 6004 Passcode: 974188)
Attachments
Subscribe to the OIST Calendar: Right-click to download, then open in your calendar application.