Professor Najwa Aaraj is the first female faculty member to join MBZUAI in the Machine Learning Department. Aaraj is Chief Researcher at the Cryptography Research Centre at the Technology Innovation Institute (TII) where she leads the research and development of cryptographic technologies, including post-quantum cryptography (PQC) software libraries and hardware implementations, lightweight cryptographic libraries for embedded and RF systems, cryptanalysis, and applied machine learning for cryptographic technologies. Most recently, Aaraj has commenced research into the intersecting area of cryptography, cybersecurity, and machine learning. She is also Acting Chief Researcher at TII’s Autonomous Robotics Research Centre, which is dedicated to breakthrough developments in robotics and autonomy.
“Given the focus of MBZUAI on artificial intelligence and machine learning, I wanted to pursue research, where you apply machine learning for cybersecurity and cryptography, and the other way around,” Aaraj said. “Typically, cryptography, cybersecurity and machine learning have been seen as three separate disciplines whereas I want to pursue cross-disciplinary research between the three of them. For example, today, we’re using machine learning for inference on edge devices. We are also using machine learning to enable or to facilitate automated cryptanalysis, both from a theoretical and practical perspective, or what we know as side channel analysis. At the same time, we’re looking at weaknesses of machine learning models including threats such as inversion, and model poisoning, then contemplating how we can use cryptography to be able to protect against such attacks.”
Aaraj is an advocate for students pursuing a career in cybersecurity, and a bigger advocate for encouraging more females to enter the technology field.
“There is a big shortage globally, both in cyber practitioners and cryptographers,” she said. “So, it is beneficial for people to have a good handle of two disciplines at a time or three disciplines at a time. For as long as I can remember, I’m one of the few women in the room. Today at TII, it’s impressive, because we have about 30%, or even 35%, female presence. One of the main aims is encouraging flexible arrangements and a mentoring-focused environment to have more women in cybersecurity, cryptography, machine learning, quantum and any other research areas. We still have a long way to go, but I think that the UAE is doing a fantastic job on this.”
The MBZUAI student body is 31% female, a number that expected to grow as more cohorts are added. Aaraj believes the next five or so years will be exciting for cryptographic technologies and cybersecurity given the rise in attacks during the pandemic, and MBZUAI and TII are positioned to contribute enormously.
“Researchers are starting to look into cyber reasoning,” she said. “The whole movement of cyber reasoning, of using machine learning for automated, vulnerability detection and incident response—especially deep learning and reinforcement learning—are proving to be promising in this area. However, there’s still a very, very long way to go.”
“Besides using machine learning for cryptography, there’s a very big need to automate incident response: today, vulnerability management is being aided by machine learning models, but you still need manual work for incident response,” Aaraj said. “A matter of seconds is already too long for you to act towards closing or patching, resolving zero-day and this is where we look at machine learning for the automation of incident responses to replace slower manual processes.”
Aaraj earned a Ph.D. with highest distinction in applied cryptography and embedded systems security from Princeton University (USA). Before joining TII, she was Senior Vice President at DarkMatter, a cybersecurity leader based in the UAE.
Aaraj has written multiple conference papers; Institute of Electrical and Electronics Engineers (IEEE) and Association for Computing Machinery (ACM) journal papers and book chapters; and received patents on applied cryptography, embedded system security, and machine learning-based protection of Internet of Things (IoT) systems.
Listen to Aaraj deliver her recent MBZUAI AI Talk on ‘How will our cryptographic toolkit be impacted by quantum computers and Machine Learning?’ on the university’s YouTube channel.
A team from MBZUAI presented a new approach for optimizing neural networks at the recent NeurIPS conference.
From optimal decision making to neural networks, we look at the basics of machine learning and how.....
MBZUAI research shows how a better understanding of the relationships between variables can benefit fundamental scientific research.