[ad_1]
Newswise — EL PASO, Texas (July 31, 2023) – Researchers are partnering to improve privacy and security of sensitive data that may contain personally identifiable information. Pacific Northwest National Laboratory (PNNL) Data Scientist Tony Chiang, DPhil, and University of Texas at El Paso Mathematical Sciences Professor Amy Wagler, Ph.D., are leading the project.
The project uses machine learning models to morph sensitive, real-world data into artificial data. The artificial data will resemble the original data in every statistical aspect and characteristic but will be shareable without compromising the privacy of those who contributed the data – and researchers will still be able to gain valuable insights from it, according to the team.
“Our model will make it highly improbable that someone could be identified,” said Wagler.
This work will be particularly helpful in the healthcare research industry, she added, where providers may be concerned about sharing results and risking patient confidentiality.
The computer model the team is making will analyze the original data and generate data that resembles it using statistical models. Then, a separate “adversary” model will try to discriminate between the two data sets.
“As soon as the model cannot discriminate between the two sets of data, we know we can work with it,” Wagler said.
Wagler and Chiang maintain joint appointments with UTEP and PNNL. Joint appointments were established to help elevate the productivity of researchers at both institutions, providing strategic capabilities that accelerate scientific impact.
Wagler said, “We are often siloed in academia, but working on shared projects with PNNL breaks down those silos and provides opportunities, professional support, and resources we need to solve these challenges.”
Shared projects also open doors for students to work with scientists from national laboratories, she said. UTEP doctoral candidates Reagan Kesseku and Cesar Vazquez have both been able to contribute to the project thanks to the partnership.
“The differential synthetic data generation project gave me the opportunity to collaborate with renowned researchers and gain exposure to cutting-edge research skills,” said Kesseku. “I learned the value of interdisciplinary collaboration and how it can drive innovation.”
A core component to the partnership between UTEP and PNNL is the commitment to investing in the future science, technology, engineering and mathematics (STEM) workforce by creating opportunities for students to have hands-on research experience, mentorship and experience in a national lab setting. Every year, hundreds of students from around the nation, including UTEP, join PNNL for internship and research associate opportunities. Every student is connected with a dedicated mentor to champion their experience and growth during their time.
“The most rewarding part of the collaboration is getting to work with Ph.D. students and helping them open their eyes to see the impact of their work,” said Chiang. “Often, Ph.D. students are solving problems for a thesis without a clear implication for the usefulness and utility of their work. As a Department of Energy National Laboratory, PNNL tackles some of the world’s pressing science and technology challenges. Having students here at PNNL affords them the opportunity to understand how their work really impacts the mission.”
Kesseku added, “The project allowed me to apply theoretical concepts to real-world data challenges, fostering critical thinking and problem-solving skills while contributing to meaningful research with practical implications.”
[ad_2]
