Nicolas Michael Müller
PulseAugur coverage of Nicolas Michael Müller — every cluster mentioning Nicolas Michael Müller across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Audio deepfake detection faces new challenges from provenance marking · 2 sources tracked
Two new research papers explore the challenges in detecting audio deepfakes, particularly when provenance marking is involved. The first paper, MADBench, introduces a benchmark that distinguishes between synthetic speec…
-
New deepfake audio detector DETECT-3B-Omni proves agnostic to content and demographics
Researchers have developed DETECT-3B-Omni, a deepfake audio detector that is agnostic to content and speaker demographics. A study using 10,240 audio samples from diverse US English speakers across 30 states, generated …
-
Audio deepfake detection flawed by watermark shortcut, study finds
A new paper, "The Watermark Shortcut," reveals a critical flaw in audio deepfake detection systems that rely on watermarking. When synthetic speech is watermarked and real speech is not, detectors incorrectly flag the w…