Deepfake Detection
Overview
Deepfake detection studies how to distinguish authentic images, video, and audio from manipulated or AI-generated content, a capability important for verification and security. Detectors look for spatial and frequency artifacts, temporal or physiological irregularities, and inconsistencies across audio, video, and semantic or physical cues; some also use pretrained foundation models, vision-language reasoning, or watermarks. Beyond classifying media, methods increasingly aim to localize altered regions or time spans, identify sources, and provide evidence-grounded explanations. A central challenge is that strong results on familiar benchmarks often fail to transfer to unseen generators, real-world conditions, or degraded media, while shortcuts, calibration, and fairness complicate reliable deployment.
Latest papers
264 papers23 papers in the last four weeks, down 30% on the four weeks before. 0.2% of all new papers.
RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation Detection
Physics-Aware Deepfake Detection via Distance-Speech Consistency
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection
EviStress: Evidence Stress Learning for Generalizable Face Forgery Detection with Textual Explanations
Not Every Cue Is Evidence: Cue Supportability for Forensic Distillation in Face Forgery Detection
Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps
RoboFake: Are Deepfake Detectors Ready for Humanoid Face Robots?
Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images
Camera-Noise Residuals for Face-Swap Detection: Redundant, Not Complementary, and Why
InstanceNorm layer placed at the noise-branch input, following the TruFor template, standardizes exactly those moments away (five-fold cross-validated AUC drops from to ). A context-crop control rules out cropping geometry, and two fixed-fusion variants that remove the bottleneck recover the statistical signal yet still fail to beat RGB on every dataset. We conclude that, on this manipulation distribution, the noise residual is redundant with RGB rather than complementary, and we give concrete guidance for practitioners adopting noise-residual fusion for face-swap detection.