preprint · arXiv preprint, 2026 · Oct 15, 2026
RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation Detection
Shukesh Reddy, Abhijit Das
In plain English
Introduces a dataset of over 2 million face-swap images covering manipulations of individual facial regions and tests 12 detectors on it. The authors report that detectors lose roughly 10% in accuracy when the swap affects only part of the face.
deepfakes
benchmark
safety