Applications of AI in Cybersecurity

Abstract: The goal of this talk is to demystify the application of artificial intelligence in the security industry. I will address common misconceptions and detail common use cases, while attempting to cut through the hype and inflated marketing claims for AI systems. I will walk through coding examples for training predictive models including spam detection and malware classification. In addition to discussing the benefits, I will also discuss potential pitfalls and challenges. The end of the talk will flip the thesis to discuss applications (or lack thereof) of cybersecurity in AI, detailing famous adversarial attacks on AI systems and methods to mitigate such attacks. Members of the target audience have a curiosity about how AI methodologies are applied in cybersecurity, but need not be experts.

Bio: Blowing stuff up in Exponent’s controlled burn room in the morning and feature engineering for deep learning computer vision models in the afternoon. This is not an atypical day for Dr. Dustin Burns, a Senior Scientist consultant in Exponent’s Statistical and Data Sciences practice. This week, he may be developing machine learning risk models to predict failure of assets of a utilities company, and next week he may be flying to the Middle East for targeted data collection for a consumer electronics company. Combining his background in laboratory experiments with his expertise in data analytics, Dr. Burns contributes to projects along the entire data science lifecycle, from experimental design and data collection, through data quality assurance, exploratory data analysis and cleaning, to modeling, visualization, and reporting.
Dustin received his Ph.D. in Physics from the University of California, Davis, in the field of experimental high-energy particle and astroparticle physics. Dustin’s dissertation research was based at the CERN Large Hadron Collider (LHC), where he worked on the team that contributed to the discovery of the Higgs boson in 2012. Dustin is a founding member of the CRAYFIS: Cosmic RAYs Found In Smartphones (http://crayfis.io) experiment, where he applied modelling and statistical techniques to design a crowd-sourced comic ray detector array using the cameras in smartphones.
In his current role at Exponent, Dustin leads a multidisciplinary team of Ph.D.’s across many industries and government agencies to respond to the world’s most impactful problems and evaluate emerging technologies using AI. The team of statisticians, machine learning developers, programmers, and cybersecurity experts can assist with developing custom algorithms, modernizing analytics programs, advising on regulatory issues (e.g. SOTIF, FDA software validation, ISO 90003/25000), and helping to evaluate intellectual property. Or just blow stuff up.