← Back to all news
arXiv Machine Learning By Danil Davydov, Bader Rasheed, Dmitriy Vatolin

Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images

Read the original on arXiv Machine Learning →

The study examines whether adding illumination inconsistencies to self-blended images—creating Temporal Self-Blended Images (T‑SBI)—enhances face‑swap detection. Across five training regimes and multiple datasets, no significant improvement in detection accuracy was observed; AUC differences stayed within seed variability. However, T‑SBI altered prediction score distributions, shifting optimal thresholds, and did improve robustness to heavy JPEG compression on the DFDC dataset, suggesting a reliance on low‑frequency cues.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 9

Camera-Noise Residuals for Face-Swap Detection: Redundant, Not Complementary, and Why

The study evaluates whether adding a camera‑noise fingerprint (Noiseprint++) to an RGB Xception backbone improves face‑swap detection on FaceForensics++. A three‑model ablation shows that fusion does not outperform RGB alone and that the residual branch alone performs near chance. Diagnostic analysis reveals that the noise maps contain a statistical signal in their per‑sample moments, but an InstanceNorm layer standardizes these away, rendering the residual redundant rather than complementary to RGB features.

By Danil Davydov, Bader Rasheed, Dmitriy Vatolin
roboticsbenchmarks
More like this →
arXiv Computer Vision
3d ago

RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation Detection

RLDF (Region-Level Deepfake) is the first dataset designed to evaluate deepfake detection on partial facial manipulations. It contains over 2 million partial face‑swap images generated with eight face‑swapping methods across seven facial regions, including both discrete (eye, nose, mouth, eyebrow) and composite regions. The authors benchmark 12 state‑of‑the‑art detectors on five cross‑dataset protocols, revealing a 10.5 % drop in AUC and 10 % drop in accuracy for region‑level detection, and propose a mask‑guided cross‑attention model as a baseline.

By Shukesh Reddy, Abhijit Das
roboticsbenchmarks
More like this →
Hugging Face Trending Papers
Jul 23

Quality-Aware Multimodal Fusion Reveals Implicit Identity in Valence-Arousal Features

Conventional face recognition relies on static appearance cues and degrades in unconstrained settings with expression variation, occlusion, and poor lighting. We hypothesize that audiovisual expression dynamics carry identity-discriminative information complementary to static appearance, and that extracting this signal requires multimodal representations robust to the variable input quality of in-the-wild video.

multimodal
More like this →
arXiv AI
Aug 26

Fidelity Preference, Not Demographic Preference: A Pixel-Level Attribute-Sensitivity Audit of Image Aesthetic/Preference Scorers

The study audits four image aesthetic scorers—LAION-Aesthetics, PickScore, ImageReward, and HPSv2—using pixel‑level interventions on skin tone and body type in both synthetic and real images. It finds that most scorers exhibit a fidelity preference: unaltered images receive the highest scores, while perturbations in either direction are penalized in an inverted‑U pattern, and this effect is largely independent of the skin operator. Synthetic‑only audits are misleading, as the apparent preference for darker skin in synthetic faces reverses or weakens when evaluated on real faces, and cross‑scorer results vary widely, underscoring the need for real‑data, within‑image causal isolation to accurately assess demographic bias.

By Mingyang Xu
diffusionbenchmarkssafety
More like this →