Dr. Senthil Periaswamy

VP of CV/ML

How did you become interested in this field?

I was drawn to this field by the realization that democracy is at stake and that misinformation is a huge threat to society.

What are you currently working on, and why is it important?

Protecting identities requires a deep understanding of human behavior. In my case, I focus on analyzing short-term behavior during video meetings. This involves closely observing how a person interacts and identifying correlations between gestures and speech—an incredibly complex and challenging task.

What problem are you trying to solve with your research?

One of my key research goals is to identify and prevent impersonators from joining video calls. These individuals use face-swap technology to appear as someone else but are unlikely to replicate their behavior convincingly. Rather than relying on low-level visual artifacts specific to the algorithms generating these fakes, my work focuses on addressing zero-day exploits by modeling human behavior.

What are the biggest challenges in this area?

One of the biggest challenges we face today in this space is the easy availability of high-quality tools that enable realistic face swaps. Additionally, our understanding of the tools and techniques used by professional criminals to create these impersonations remains limited.

How could your work change the way people interact with digital media?

My work has the potential to fundamentally shift how people interact with digital media by making identity verification more behavior-based rather than appearance-based. As face-swapping and deepfake technologies become more sophisticated, traditional visual cues are no longer reliable. By focusing on behavioral modeling—how people speak, gesture, and respond in real-time—we can build systems that are harder to deceive and more attuned to authentic human presence. This could lead to more secure video communications, reduce the spread of impersonation-based fraud, and ultimately help restore trust in digital interactions.

What’s the biggest lesson you’ve learned as a researcher?

Even when researchers pursue the same high-level approach to tackling a problem, their outcomes can vary greatly. If an approach doesn’t yield favorable results, the issue often lies in the specific decisions made during the problem-solving process. Success is rarely about the approach alone—it comes from experience, learning through mistakes, and the persistence to keep refining the path forward.

How do you stay motivated and creative in your work?

Working and collaborating with a talented team is invaluable. Equally important is being genuinely passionate about the work you're doing—it fuels creativity and resilience. I've also found that spending time outdoors while thinking through a problem can make a big difference. Sometimes, thinking outside the box literally means stepping outside the office or home.

What excites you most about GetReal’s future?

We’re dreaming big. We’re fortunate to be working with one of the pioneers in the field, Dr. Hany Farid. Backed by a strong cybersecurity foundation and supported by an incredibly talented team of researchers, we’re pushing the boundaries of what’s possible.