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

Shukesh Reddy; Abhijit Das

cs.CVOct 15, 2026

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

Authors: Shukesh Reddy, Abhijit Das

Organizations: Machine Intelligence Group, Department of CS&IS Birla Institute of Technology and Science, Pilani, Hyderabad Campus, India

Abstract

Existing deepfake detection models are built upon manipu- lated images that are tampered with either exclusively fully swapped or fully synthesised faces, which leads us to an open question: Can off-the-shelf deepfake models detect manipulation effectively while tampering is confined to a local facial sub-region? To fill this gap, we introduce RLDF (Region-Level Deepfake), the first dataset for region-level deepfake evaluation. Employing the proposed region-aware partial swap synthesis model, we generate over 2M par- tial face-swap images by using eight face-swapping meth- ods. Altogether, we considered seven face regions, among which there are four discrete regions (eye, nose, mouth and eyebrow) and four composite facial regions (eye and nose; eye, nose and mouth; eye, nose, mouth and eye- brow; and full face). In addition, we define three evalu- ation protocols and benchmark 12 state-of-the-art detectors across the five popular standard cross-dataset evaluations, DF40, and the proposed RLDF, providing a comprehen- sive audit of where and why existing detectors underper- formed. Our evaluation reveals that existing detectors fail to generalize consistently across partial facial regions, re- sulting in an overall drop of 10.5% AUC and 10% accu- racy under region-level evaluation. Further, we propose a mask-guided cross-attention model as a baseline approach that can effectively detect region-level manipulation. The proposed dataset, code, and checkpoints are available at https://github.com/RLDF-Dataset/RLDF.

Figures & tables

Dataset	Pub.	#Methods	Fake Images	Region Labels	Localization GT	Partial-Face
DF-TIMIT [ 27 ]	ArXiv’18	2	–	✗	✗	✗
UADFV [ 68 ]	ICASSP’19	1	252	✗	✗	✗
FaceForensics++ [ 52 ]	ICCV’19	4	–	✗	✗	✗
DeepFakeDetection [ 17 ]	–	5	–	✗	✗	✗
CDF [ 35 ]	CVPR’20	1	–	✗	✗	✗
DFFD [ 12 ]	CVPR’20	7	0.2M+	✗	✗	✗

Table 1: Comparison of existing deepfake datasets. All prior datasets annotate manipulation with a binary image-level label and contain only full-face swaps. RLDF is the first benchmark to provide region-level annotations for partially manipulated faces. Region Labels : per-region GT labels across 8 sub-facial areas. Localization GT : spatial ground-truth for forgery localization. Partial-Face : manipulation on sub-regions only.

Figure 1: Overview of the proposed region-aware partial swap synthesis: Given source–target video pairs, (1) aligned face crops are extracted and passed through eight face-swapping methods to generate full face-swaps, (2) a BiSeNetV2 facial parser derives soft region masks from the target frame, and (3) the designated facial region from the full swap is composited back onto the target image, producing partial fakes across eight facial regions. Representative samples for every region and swap method are provided in Appendix F.

Figure 2: Overview of the proposed mask-guided cross-attention framework . A partially fine-tuned CLIP ViT-L/14 encoder extracts $N{=}256$ patch tokens. Forgery MaskNet assigns each patch a forgery score $\hat{m}_{i}\in[0,1]$ . Masked Cross-Attention uses these scores as attention biases so the model focuses on suspicious patches. A global feature (mean-pooled) and the region-focused feature are concatenated and passed to a classifier.

Figure 3: t-SNE visualization of penultimate features on the RLDF test set (Protocol #3). Blue = real, red = fake.

Detector	Venue	CelebDF-v1		CelebDF-v2		DFDC		DFDCP		UADFV		Wtd. Mean
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.69	0.77	0.71	0.74	0.64	0.71	0.68	0.73	0.79	0.94	0.67	0.73
F3Net [ 46 ]	ECCV’20	0.68	0.75	0.61	0.73	0.63	0.70	0.64	0.70	0.81	0.89	0.63	0.71
RECCE [ 5 ]	CVPR’22	0.69	0.75	0.70	0.75	0.62	0.68	0.66	0.70	0.78	0.89	0.64	0.70
SBI [ 53 ]	CVPR’22	0.75	0.81	0.71	0.77	0.62	0.71	0.74	0.83	0.84	0.94	0.69	0.77
LGrad [ 57 ]	CVPR’23	0.39	0.54	0.35	0.53	0.48	0.50	0.35	0.50	0.50	0.51	0.41	0.50

Table 2: Protocol #1 (Cross-Dataset, Classic Deepfake Benchmarks): Frame-level performance. Models are trained on FF++ and tested on five widely-used deepfake benchmarks. Bold = best; underline = second-best (per metric, per column). Weighted mean is image-count weighted across five datasets (total 297,914 images; DFDC+DFDCP account for 92.5% of weight).

Panel of Figure 4 — Figure 4: ROC curves across all three evaluation protocols. Our baseline (8-Blk, 12-Blk) achieves competitive AUC across all protocols (P#1: $0.906$ , P#2: $0.788$ , P#3: $0.88$ ), while existing detectors show inconsistent performance under region-level evaluation.

Detector	Venue	Deep- FaceLab		Mid- Journey6		Hey- Gen		Star- GAN		Star- GAN2		Style- CLIP		Collab- Diff		Which- FaceReal		Wtd. Mean
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.66	0.72	0.62	0.57	0.79	0.77	0.57	0.62	0.48	0.42	0.65	0.78	0.69	0.75	0.47	0.45	0.65	0.67
F3Net [ 46 ]	ECCV’20	0.58	0.71	0.72	0.78	0.50	0.50	0.59	0.67	0.48	0.39	0.42	0.44	0.54	0.42	0.44	0.34	0.52	0.53
RECCE [ 5 ]	CVPR’22	0.57	0.64	0.68	0.72	0.71	0.55	0.55	0.61	0.48	0.38	0.50	0.61	0.60	0.56	0.47	0.40	0.59	0.56
SBI [ 53 ]	CVPR’22	0.72	0.80	0.55	0.57	0.67	0.71	0.71	0.81	0.52	0.52	0.67	0.68	0.53	0.55	0.40	0.34	0.63	0.67
LGrad [ 57 ]	CVPR’23	0.33	0.48	0.99	1.00	0.75	0.44	0.50	0.53	0.50	0.49	0.26	0.46	0.51	0.61	0.67	0.76	0.56	0.53

Table 3: Protocol #2 (Cross-Dataset, DF40 Test Set): Frame-level performance. Models are trained on FF++ and tested on eight generation methods from DF40. Bold = best; underline = second-best (per metric, per column). Weighted mean is image-count weighted across the eight sub-datasets (total 31,238 images).

Detector	Venue	BlendFace		E4S		FaceDancer		FSGAN		Ghost		InSwapper		SimSwap		UniFace		RLDF: All		Wtd. Mean
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.66	0.73	0.70	0.78	0.69	0.76	0.80	0.88	0.69	0.77	0.79	0.87	0.66	0.74	0.68	0.74	0.71	0.78	0.71	0.78
F3Net [ 46 ]	ECCV’20	0.59	0.69	0.69	0.79	0.61	0.72	0.81	0.92	0.66	0.80	0.84	0.93	0.63	0.77	0.59	0.69	0.68	0.79	0.68	0.79
RECCE [ 5 ]	CVPR’22	0.62	0.71	0.75	0.84	0.66	0.75	0.82	0.91	0.70	0.80	0.84	0.92	0.67	0.77	0.64	0.73	0.71	0.80	0.71	0.81
SBI [ 53 ]	CVPR’22	0.70	0.81	0.93	0.98	0.62	0.74	0.77	0.88	0.70	0.79	0.81	0.89	0.67	0.78	0.71	0.82	0.74	0.84	0.74	0.84
LGrad [ 57 ]	CVPR’23	0.50	0.54	0.50	0.57	0.50	0.53	0.49	0.48	0.50	0.57	0.50	0.59	0.50	0.58	0.50	0.53	0.50	0.55	0.50	0.55

Table 4: Protocol #3 (RLDF Region-Level Test Set): Frame-level performance. Models are trained on FF++ and evaluated on our proposed RLDF benchmark across eight face-swap methods. Bold = best; underline = second-best (per metric, per column). Weighted mean is image-count weighted (total 286,456 images; counts are near-uniform so weighting is effectively equal).

Detector	Venue	P#1 (Classic)		P#2 (DF40)		P#3 (RLDF)		Mean
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.67	0.73	0.65	0.67	0.71	0.78	0.68	0.73
F3Net [ 46 ]	ECCV’20	0.63	0.71	0.52	0.53	0.68	0.79	0.61	0.68
RECCE [ 5 ]	CVPR’22	0.64	0.70	0.59	0.56	0.71	0.81	0.65	0.69
SBI [ 53 ]	CVPR’22	0.69	0.77	0.63	0.67	0.74	0.84	0.69	0.76
LGrad [ 57 ]	CVPR’23	0.41	0.50	0.56	0.53	0.50	0.55	0.49	0.53

Table 5: Cross-Protocol Generalization. Our detector is the only method maintaining strong performance across all three regimes. Bold = best, underline = second-best (per metric, per column).

Variant	Absolute Performance						$\Delta$ vs Full Model
	P1 (Classic)		P2 (DF40)		P3 (RLDF)		P1 (Classic)		P2 (DF40)		P3 (RLDF)
	ACC	AUC	ACC	AUC	ACC	AUC	$\Delta$ ACC	$\Delta$ AUC	$\Delta$ ACC	$\Delta$ AUC	$\Delta$ ACC	$\Delta$ AUC
w/o mask guidance	0.772	0.852	0.749	0.780	0.607	0.850	$+$ 0.001	$+$ 0.000	$-$ 0.051	$-$ 0.060	$\mathbf{-0.155}$	$-$ 0.011
w/o forged path ( $\mathbf{F}_{f}{=}\mathbf{F}_{g}$ )	0.771	0.851	0.748	0.774	0.605	0.850	$+$ 0.001	$-$ 0.001	$-$ 0.052	$-$ 0.066	$\mathbf{-0.157}$	$-$ 0.012
w/o global path ( $\mathbf{F}_{g}{=}\mathbf{F}_{f}$ )	0.770	0.850	0.749	0.779	0.617	0.850	$-$ 0.001	$-$ 0.001	$-$ 0.051	$-$ 0.061	$-$ 0.144	$-$ 0.011
Hard mask (binary $\hat{\mathbf{m}}$ )	0.764	0.851	0.748	0.780	0.648	0.851	$-$ 0.007	$-$ 0.001	$-$ 0.052	$-$ 0.060	$-$ 0.113	$-$ 0.011

Table 6: Ablation Study. Component-wise analysis of the proposed Mask-Guided Cross-Attention (MCA) framework across three evaluation protocols: P1 (classic cross-dataset), P2 (DF40), and P3 (RLDF region-level benchmark).

\Delta

denotes the difference from the full model (negative indicates performance drop).

#	Method	Paradigm	Venue	Key characteristic	Code
1	BlendFace [ 55 ]	GAN, disentangle	ICCV 2023	Seam-minimising latent blending; hardest to detect	Link
2	E4S [ 38 ]	Latent inversion	CVPR 2023	Style-transfer boundaries; most detectable	Link
3	FaceDancer [ 51 ]	GAN, disentangle	WACV 2023	Adaptive feature injection across identities	Link
4	FSGAN [ 42 ]	Reenactment-guided	ArXiv 2019	Parsing-mask-based subject-agnostic swap	Link
5	GHOST [ 18 ]	GAN, lightweight	ArXiv 2022	Efficient one-shot swap with strong colour consistency	Link
6	InSwapper [ 61 ]	GAN (Roop)	—	Commercial-grade; widely used in real-world deepfakes	Link

Table S1: Face-swapping methods used in RLDF construction.

Figure S1: Human Perceptual Realism Survey. Per-region mean fakeness score (0 = real, 5 = obviously fake) rated by 37 participants across 14 region-level deepfake images. Dashed line = midpoint (2.5); dotted red line = overall mean (2.34). Partial-region fakes score below the midpoint; Full-Face fakes are the most perceptually detectable.

Figure S4: Dataset samples: Eye region (pair 081/087).

Figure S5: Dataset samples: Nose region (pair 081/087).

Figure S6: Dataset samples: Mouth region (pair 081/087).

Figure S7: Dataset samples: Composite-1 (Eye+Nose) region (pair 081/087).

Figure S8: Dataset samples: Composite-2 (Eye+Nose+Mouth) region (pair 081/087).

Figure S9: Dataset samples: Composite-3 (Eye+Nose+Mouth+Eyebrow) region (pair 081/087).

Figure S10: ROC curves averaged per manipulation region (Protocol #3). Detection AUC degrades as region size decreases, with Eye being the hardest.

Figure S11: ROC curves averaged per face-swap method (Protocol #3). E4S is the most detectable; BlendFace is the hardest.

Figure S12: AUC heatmap: Ours (12-Blk) . Most uniform coverage.

Figure S13: AUC heatmap: Ours (8-Blk) . Slightly stronger on small regions.

Figure S14: AUC heatmap: Effort . Strong on full face, weakens for single-region.

Figure S15: AUC heatmap: FatFormer . High on E4S, collapses on BlendFace.

Figure S16: AUC heatmap: ProDet . Strong on Full Face, poor on small regions.

Figure S17: Confusion matrix: Ours (8-Blk) . Most balanced FP/FN across all regions.

Figure S18: Confusion matrix: Effort . High false-negative rate on single-region fakes.

Figure S19: Confusion matrix: ProDet . High FN on sub-region fakes, strong on full face.

Figure S20: Confusion matrix: FatFormer . Elevated false-positive rate on real images.

Figure S21: t-SNE of penultimate features on the RLDF test set. Blue = Real, Red = Fake. Our models achieve cleaner separation than competitors.

Figure S22: Ours (12-Blk) : Per-region t-SNE visualization

Figure S23: Ours (8-Blk) : Per-region t-SNE visualization

Figure S24: Effort : Per-region t-SNE visualization

Figure S25: ProDet : Per-region t-SNE visualization

Figure S26: SBI : Per-region t-SNE visualization

Figure S27: FatFormer : Per-region t-SNE visualization

Panel of Figure 38 — Figure S28: MaskNet activation on unseen cross-dataset benchmarks. Despite training exclusively on FF++, MaskNet produces structured, face-centric masks across CelebDF, DFDC, DFDCP, and UADFV, consistently activating around eyes, nose, and mouth.

Panel of Figure 39 — Figure S29: MaskNet activation: BlendFace across all 7 regions. Each panel is the mean per-patch forgery score $\hat{\mathbf{m}}$ heatmap. Without any spatial supervision, MaskNet progressively expands its focus as the manipulated region grows.

Panel of Figure 40 — Figure S30: MaskNet activation: Eye region across all 8 swap methods. All methods show consistent eye-patch focus. Activation intensity correlates with detectability: BlendFace (AUC 0.85) produces diffuse masks, while E4S and FaceDancer (AUC $\geq$ 0.96) yield sharp, localised activations.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.62	0.68	0.64	0.70	0.66	0.73	0.66	0.72	0.70	0.78	0.71	0.79	0.72	0.83
F3Net [ 46 ]	ECCV’20	0.56	0.66	0.55	0.64	0.59	0.69	0.56	0.67	0.60	0.72	0.62	0.75	0.67	0.81
RECCE [ 5 ]	CVPR’22	0.59	0.68	0.59	0.68	0.58	0.69	0.61	0.71	0.61	0.73	0.64	0.76	0.67	0.78
SBI [ 53 ]	CVPR’22	0.62	0.73	0.62	0.73	0.60	0.72	0.70	0.82	0.76	0.87	0.77	0.89	0.85	0.94
LGrad [ 57 ]	CVPR’23	0.50	0.54	0.50	0.53	0.50	0.53	0.50	0.54	0.50	0.54	0.50	0.54	0.50	0.53

Table S2: Protocol #3 (BlendFace): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Figure S31: Ours (12-Blk) : Per-region real/fake score distributions.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.70	0.75	0.70	0.77	0.74	0.82	0.71	0.77	0.67	0.74	0.70	0.78	0.71	0.83
F3Net [ 46 ]	ECCV’20	0.68	0.78	0.70	0.79	0.72	0.82	0.67	0.76	0.68	0.76	0.69	0.79	0.55	0.66
RECCE [ 5 ]	CVPR’22	0.74	0.81	0.80	0.88	0.66	0.77	0.81	0.89	0.73	0.83	0.76	0.85	0.64	0.76
SBI [ 53 ]	CVPR’22	0.88	0.92	0.92	0.98	0.89	0.96	0.95	1.00	0.95	1.00	0.95	1.00	0.95	1.00
LGrad [ 57 ]	CVPR’23	0.50	0.56	0.50	0.56	0.50	0.57	0.50	0.57	0.50	0.58	0.50	0.57	0.50	0.58

Table S3: Protocol #3 (E4S): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Figure S32: Eye vs Full Face score distributions. Eye shows near-complete real/fake overlap, Full Face shows clear bimodal separation.

Figure S33: Effort : Per-region real/fake score distributions.

Figure S34: ProDet : Per-region real/fake score distributions.

Figure S35: FatFormer : Per-region real/fake score distributions.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.63	0.69	0.67	0.74	0.67	0.75	0.68	0.76	0.74	0.81	0.73	0.80	0.73	0.85
F3Net [ 46 ]	ECCV’20	0.58	0.67	0.61	0.72	0.58	0.68	0.62	0.73	0.65	0.76	0.65	0.76	0.74	0.84
RECCE [ 5 ]	CVPR’22	0.61	0.68	0.65	0.73	0.64	0.75	0.66	0.74	0.71	0.81	0.70	0.80	0.79	0.87
SBI [ 53 ]	CVPR’22	0.58	0.68	0.56	0.67	0.56	0.65	0.61	0.74	0.63	0.77	0.64	0.78	0.77	0.89
LGrad [ 57 ]	CVPR’23	0.50	0.53	0.50	0.54	0.50	0.54	0.50	0.53	0.50	0.53	0.50	0.52	0.50	0.52

Table S4: Protocol #3 (FaceDancer): Region-level performance (ACC / AUC). Bold = best; underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.67	0.75	0.76	0.84	0.82	0.91	0.79	0.88	0.86	0.96	0.85	0.94	0.85	0.95
F3Net [ 46 ]	ECCV’20	0.64	0.80	0.76	0.89	0.80	0.91	0.81	0.92	0.90	0.97	0.87	0.95	0.92	0.98
RECCE [ 5 ]	CVPR’22	0.68	0.79	0.78	0.88	0.86	0.93	0.82	0.91	0.90	0.97	0.88	0.95	0.91	0.98
SBI [ 53 ]	CVPR’22	0.64	0.77	0.69	0.83	0.66	0.79	0.80	0.91	0.86	0.95	0.86	0.95	0.87	0.96
LGrad [ 57 ]	CVPR’23	0.49	0.48	0.49	0.48	0.49	0.48	0.49	0.48	0.49	0.49	0.49	0.49	0.49	0.48

Table S5: Protocol #3 (FSGAN): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.61	0.68	0.65	0.72	0.74	0.82	0.64	0.73	0.74	0.82	0.76	0.84	0.77	0.88
F3Net [ 46 ]	ECCV’20	0.61	0.76	0.61	0.76	0.67	0.82	0.61	0.77	0.67	0.81	0.73	0.87	0.61	0.79
RECCE [ 5 ]	CVPR’22	0.64	0.73	0.67	0.77	0.72	0.83	0.66	0.78	0.73	0.83	0.76	0.86	0.57	0.65
SBI [ 53 ]	CVPR’22	0.61	0.70	0.62	0.70	0.60	0.67	0.72	0.83	0.78	0.88	0.77	0.88	0.77	0.90
LGrad [ 57 ]	CVPR’23	0.49	0.57	0.50	0.57	0.50	0.57	0.50	0.57	0.50	0.57	0.50	0.57	0.50	0.57

Table S6: Protocol #3 (GHOST): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.64	0.73	0.79	0.87	0.81	0.88	0.81	0.89	0.86	0.94	0.83	0.91	0.84	0.93
F3Net [ 46 ]	ECCV’20	0.70	0.86	0.84	0.94	0.80	0.91	0.89	0.96	0.92	0.98	0.88	0.96	0.86	0.95
RECCE [ 5 ]	CVPR’22	0.67	0.79	0.85	0.93	0.86	0.95	0.84	0.93	0.90	0.98	0.88	0.96	0.87	0.95
SBI [ 53 ]	CVPR’22	0.68	0.79	0.73	0.85	0.61	0.73	0.88	0.96	0.93	0.98	0.92	0.98	0.91	0.97
LGrad [ 57 ]	CVPR’23	0.50	0.59	0.50	0.60	0.50	0.60	0.50	0.59	0.49	0.59	0.50	0.58	0.50	0.59

Table S7: Protocol #3 (InSwapper): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.62	0.69	0.63	0.70	0.70	0.78	0.63	0.71	0.69	0.77	0.70	0.79	0.70	0.82
F3Net [ 46 ]	ECCV’20	0.60	0.75	0.60	0.75	0.64	0.79	0.61	0.74	0.63	0.78	0.64	0.80	0.59	0.73
RECCE [ 5 ]	CVPR’22	0.63	0.73	0.63	0.73	0.69	0.80	0.65	0.75	0.68	0.80	0.69	0.81	0.61	0.70
SBI [ 53 ]	CVPR’22	0.58	0.67	0.58	0.68	0.58	0.67	0.67	0.78	0.74	0.86	0.74	0.86	0.82	0.92
LGrad [ 57 ]	CVPR’23	0.50	0.58	0.50	0.58	0.50	0.58	0.50	0.58	0.50	0.58	0.50	0.58	0.50	0.58

Table S8: Protocol #3 (SimSwap): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Detector	Venue	Eye		Nose		Mouth		C-1		C-2		C-3		Full
		ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC	ACC	AUC
Xception [ 52 ]	ICCV’19	0.61	0.67	0.67	0.73	0.67	0.74	0.68	0.74	0.71	0.79	0.70	0.78	0.71	0.81
F3Net [ 46 ]	ECCV’20	0.55	0.63	0.57	0.68	0.57	0.69	0.58	0.68	0.60	0.72	0.60	0.71	0.67	0.80
RECCE [ 5 ]	CVPR’22	0.59	0.67	0.63	0.72	0.61	0.72	0.66	0.75	0.68	0.78	0.67	0.77	0.78	0.86
SBI [ 53 ]	CVPR’22	0.67	0.79	0.60	0.72	0.59	0.71	0.72	0.84	0.77	0.88	0.78	0.89	0.83	0.93
LGrad [ 57 ]	CVPR’23	0.50	0.53	0.50	0.53	0.50	0.54	0.50	0.53	0.50	0.53	0.50	0.53	0.50	0.52

Table S9: Protocol #3 (UniFace): Region-level performance (ACC / AUC). Bold = best, underline = second-best (per metric, per column). C-1: eye

+

nose, C-2: eye

+

nose

+

mouth, C-3: eye

+

nose

+

mouth

+

eyebrow.

Figure S36: MaskNet visualization: predicted forgery responses highlighting manipulated regions.

Figure S37: Failure cases: Eye region. Fake images predicted as Real by Ours (12-Blk).

Figure S39: Failure cases: Mouth region.

Figure S40: Failure cases: Composite-1 (Eye+Nose).

Figure S41: Failure cases: Composite-2 (Eye+Nose+Mouth).

Figure S42: Failure cases: Composite-3 (Eye+Nose+Mouth+Eyebrow).

Figure S43: Failure cases: Full Face region.

Deepfake Detection

Deepfake detection identifies manipulated or AI-generated media to support trustworthy communication, identity verification, and forensic analysis.

See all 241 papers

Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection
Mar 27, 2026Kutub Uddin, Nusrat Tasnim, Byung Tae OhDeepfake Detection
The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection
May 11, 2026Andrii Yermakov, Jan Cech, Mario Fritz +1Image Forgery Detection Deepfake Detection
Czech Technical University in Prague · CISPA Helmholtz Center for Information Security
FairReL: Deepfake Detection using Fairness-Aware Representation Learning
Aug 28, 2026Xiaoman Lu, Jiaqi Li, Shuntian Zheng +2Deepfake Detection Algorithmic Fairness
Department of Computer Science University of Warwick Coventry, United Kingdom · School of Computer Science University of Birmingham Birmingham, United Kingdom

Mar 27, 2026J/K move · Enter open · S save

Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection

Kutub Uddin, Nusrat Tasnim, Byung Tae Oh

Deepfake Detection

Open paper AskPDF arXiv

Multimedia data, particularly images and videos, is integral to various applications, including surveillance, visual interaction, biometrics, evidence gathering, and advertising. However, amateur or skilled counterfeiters can simulate them to create deepfakes, often for slanderous motives. To address this challenge, several forensic methods have been developed to ensure the authenticity of the content. The effectiveness of these methods depends on their focus, with challenges arising from the diverse nature of manipulations. In this article, we analyze existing forensic methods and observe that each method has unique strengths in detecting deepfake traces by focusing on specific facial regions, such as the frame, face, lips, eyes, or nose. Considering these insights, we propose a novel hybrid approach called Face2Parts based on hierarchical feature representation (

HFR

) that takes advantage of coarse-to-fine information to improve deepfake detection. The proposed method involves extracting features from the frame, face, and key facial regions (i.e., lips, eyes, and nose) separately to explore the coarse-to-fine relationships. This approach enables us to capture inter-dependencies among facial regions using a channel-attention mechanism and deep triplet learning. We evaluated the proposed method on benchmark deepfake datasets in both intra-, inter-dataset, and inter-manipulation settings. The proposed method achieves an average AUC of 98.42% on FF++, 79.80% on CDF1, 85.34% on CDF2, 89.41% on DFD, 84.07% on DFDC, 95.62% on DTIM, 80.76% on PDD, and 100% on WLDR, respectively. The results demonstrate that our approach generalizes effectively and achieves promising performance to outperform the existing methods.

Abstract

Deepfake Detection

Explore similar work

Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection

The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection

FairReL: Deepfake Detection using Fairness-Aware Representation Learning