Microsoft · IEEE Spectrum AI
Deepfake Detection Dataset Aims to Keep Up With Generative AI
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
◌ Single Source
The May issue of IEEE Spectrum is here!
Key facts
- The researchers describe their new dataset, called the Microsoft-Northwestern-Witness (MNW) deepfake detection benchmark, in a study published 10 April in IEEE Intelligent Systems
- This article is part of their exclusive IEEE Journal Watch series in partnership with IEEE Xplore
- None of them could achieve this alone,” says Macro Postiglione, a post-doctoral researcher at Northwestern University
- Thomas Roca is a principal research scientist at Microsoft who researches security around generative AI
Summary
The MNW benchmark pulls from more sources and will be updated regularly. This article is part of their exclusive IEEE Journal Watch series in partnership with IEEE Xplore. With the rise of AI-generated content online, it’s becoming more difficult—and more important—to help the public identify whether an image, audio clip or video is real or fake. The researchers describe their new dataset, called the Microsoft-Northwestern-Witness (MNW) deepfake detection benchmark, in a study published 10 April in IEEE Intelligent Systems. Thomas Roca is a principal research scientist at Microsoft who researches security around generative AI.