Real-Time Deepfake Detection Method Deepfake Detection Method created.  NYU Tandon

NYU researchers develop a new real-time deepfake detection method for videos and audio.

Deepfake videos and audio, created using artificial intelligence, are increasingly used maliciously.

Associate Professor Chinmay Hegde is leading efforts in this area, aiming to protect the integrity of media and digital communication by finding effective solutions to the deepfake challenge.

He is exploring challenge-response systems for detecting audio and video deepfakes.

These realistic manipulations can deceive viewers, spread misinformation, and harm reputations, impacting areas like politics, identity theft, and cybercrime.

As deepfake technology becomes more advanced and accessible, the potential for harm grows. Recognizing this threat, NYU Tandon researchers are developing new ways to detect and counter deepfakes.

Hegde said:

“Broadly, I’m interested in AI safety in all of its forms. And when a technology like AI develops so rapidly and gets good so quickly, it’s an area ripe for exploitation by people who would do harm.”

source SpectrumNYU Tandon School of Engineering