What if a machine, like a human, could learn from its mistakes?

This question has served as the backbone for many a science fiction novel, but for 2012 Buffalo High School graduate Shaya Wolf, it is no rhetorical question.

Wolf, the daughter of Kerry Wolf and Mary Wolf, is spending her summer vacation at Idaho National Laboratory in Idaho Falls studying secured embedded intelligence – a way for industrial systems in the oil and gas industry to learn from power failures and malicious attacks so that they can operate at a higher level in the future.

“Secure embedded intelligence is a way to provide more reliable security to match the more intelligent energy solutions necessary to our communities,” Wolf said in an email interview with the Buffalo Bulletin. “Secure embedded intelligence leverages sensor readings against machine learning algorithms to create systems that can learn from not only non-malicious faults, but also adversarial attacks. This means that our systems could learn from vulnerabilities to become more secure in the future.”

Idaho National Laboratory, one of the labs under the U.S. Department of Energy, dedicates itself to providing safe and secure energy through multidisciplinary research and development across engineering, computer science and business. Wolf, who is pursuing her doctorate in cybersecurity, is one of four University of Wyoming students participating in the 10-week internship at INL. She is joined by fellow computer science Ph.D. student Rafer Cooley, mechanical engineering senior Joe Klebba and chemical engineering senior Maxon Lube.

“This internship is wildly open, meaning that what we do/study/create/fix/leverage is completely up to us to discover,” Wolf said. “We are starting from the beginning and researching what has already been done in this field to find the edge of current research. This allows us to find novel solutions and genuine goals that build on past research and boldly go where no man has gone before.”

Wolf said that she and her fellow students are researching such areas as nuclear microreactors, oil and gas infrastructures, embedded intelligence, common attacks against industrial control systems and the economics of viable critical infrastructure solutions.

Creating industrial systems that can learn from and fix their own problems could be a huge step forward for the oil and gas industries – both in Johnson County and across the state, Wolf said. It could reduce the need for unnecessary routine maintenance, decrease operations costs and create safer solutions to problems not easily or safely addressed by humans.

Wolf has three years left in pursuit of her doctorate and said she hopes to continue researching cybersecurity issues by partnering with both academia and industry. Wolf said that the internship at INL will give her a great foundation to build on as she continues her research.

“Internships like this are invaluable for students that want to make a difference,” Wolf said. “Working with students from other backgrounds/fields helps us all think a little differently and expand on how we learn. We all solve problems differently, but the true power in an internship like this is being able to view one very important problem from many different viewpoints to find a common solution that is ideal for everyone. We hope to find intelligent solutions to problems facing our nation, to publish our findings and push the edge of secure embedded intelligence in industrial control systems. But we also hope to do that in a very specific way: through collaboration and cooperation.”

(0) comments

Welcome to the discussion.

Keep it Clean. Please avoid obscene, vulgar, lewd, racist or sexually-oriented language.
PLEASE TURN OFF YOUR CAPS LOCK.
Don't Threaten. Threats of harming another person will not be tolerated.
Be Truthful. Don't knowingly lie about anyone or anything.
Be Nice. No racism, sexism or any sort of -ism that is degrading to another person.
Be Proactive. Use the 'Report' link on each comment to let us know of abusive posts.
Share with Us. We'd love to hear eyewitness accounts, the history behind an article.