Adversarial attacks and deepfakes: How the computer science program is engaging students in artificial intelligence and cybersecurity research
Adversarial attacks and deepfakes: How the computer science program is engaging students in artificial intelligence and cybersecurity research
UDC was awarded a $152,350 grant in August 2021 by Computer and Network Systems to partner with researchers from six other Historically Black Colleges and Universities (HBCUs)—Hampton University, Florida A&M University, Winston-Salem State University, Norfolk State University, Mississippi Valley State University and Howard University—and three National Research Laboratories (NRLs) —Lawrence-Livermore, Brookhaven and National Renewable Energy.
The project began on November 1 with a goal to educate and engage students in research efforts in artificial intelligence (AI) and cybersecurity (CyS). UDC’s team includes Dr. Briana Wellman, Dr. Lily R. Liang and Dr. Timothy Oladunni of the computer science program.
Cybersecurity vulnerabilities are growing at a scale and speed that strains human capacity to address threats proactively. Thus, developing AI and machine learning (ML) techniques to support prediction and detection capabilities is an important area of research. The HBCUs involved in AI-CyS either already have or are rapidly developing cybersecurity research capacity that would be further developed by increasing student and faculty involvement and training.
To develop that potential the project team will leverage its existing research activities and collaborations to deepen relationships with other HBCUs and with the NRLs. The NRLs will provide additional research resources and mentoring through regular remote meetings and on-site visits to the NRLs around projects of mutual interest and opportunities for student internships and faculty visits at the NRLs.
The team will also work to expand the impact of the partnership by:
- Hosting an annual research conference to bring researchers together across the partners
- Adding additional research projects, HBCUs and national lab partners with complementary research and educational interests to the existing partnership
- Developing cross-university curricula and mentoring programs to train HBCU students to be future research and workforce leaders in cybersecurity.
Together, these efforts will advance research in cybersecurity, research capacity at the partner institutions and research and educational opportunities for students at HBCUs, often members of underrepresented groups in computing.
“Our UDC team is very excited about this research partnership and the opportunities it offers to our students and faculty,” said Liang. “We have met with the national labs, recruited students and had a kick-off research workshop with about 20 HBCU faculty in attendance.”
Jeffrey Enamorado, a senior computer science major working on the project is impressed by how much he’s already learned.
“I took a class on artificial intelligence with Dr. Liang and it tremendously grew my interest. I wanted to learn how to solve problems using this technology,” Enamorado said. “For example, deepfakes are becoming more of a problem in media, and I wanted to combat that.”
The partnership will be organized around five seed research projects chosen to maximize existing capacity and collaborations. The first will use reinforcement learning to improve target selection by current autonomous network mapping software agents. The second involves analyzing network traceroute data to better understand and work around limitations of its ability to map paths to better detect and classify network anomalies. The third focuses on developing, then defending against, adversarial attacks on computer vision algorithms in which attackers add visual patches to objects to fool object detection and classification tools. The fourth will analyze existing tools and algorithms for generating deepfakes to develop methods to detect forged video in near real-time, with applications to surveillance and authentication tasks. The fifth will extend probabilistic sequential models to develop threat detectors at multiple levels of the network stack in the context of the Internet of Things devices.
Beyond these specific seed research projects, the project team will also analyze its activities to develop evidence-based best practices for research capacity-building efforts. The efforts will include developing mechanisms to expand current collaborations and foster resources, sharing expertise between HBCU members and hosting an annual research conference that allows faculty and students from existing and potential partner HBCUs to showcase their cybersecurity research and create connections with other researchers and resources.
For more information about UDC’s computer science program, click here.
