A Novel Unified Approach to Deepfake Detection

Lord Sen; Shyamapada Mukherjee

cs.CVJan 6, 2026

A Novel Unified Approach to Deepfake Detection

Authors: Lord Sen, Shyamapada Mukherjee

Organizations: Computer Science and Engineering NIT Rourkela Rourkela, Odisha

Abstract

Advancements in the field of AI are increasingly giving rise to various threats, one of the most prominent being the synthesis and misuse of deepfakes. To sustain trust in this digital age, the detection and tagging of deepfakes are essential. In this paper, a novel architecture for deepfake detection in images and videos is presented. The architecture uses cross-attention between spatial and frequency domain features to classify an image as real or fake. This paper aims to develop a unified architecture and provide insights into each step. Through this approach, we achieve results competitive with the State-of-the-Art (SOTA). Furthermore, this approach generalizes well to cross-dataset testing, which is evident from the experimental results.

Figures & tables

Fig. 1: Distributions of global spatial intensity moments across the dataset for authentic (blue) and manipulated (red) faces: Global Pixel Mean, Variance, Skewness, and Kurtosis.

Fig. 2: Empirical distributions (mean line with shaded $\pm 1\sigma$ standard deviation envelope) of Sub-band Energy, Spectral Entropy, and Power Spectral Density across 8 radial frequency bands computed exclusively over dlib -extracted facial crops for authentic (blue) and manipulated (red) images.

Fig. 3: Continuous spectral and spatial residual analysis across authentic (blue) and manipulated (red) cohorts: (Left) 1D continuous azimuthal radial power spectrum

\bar{S}(r)

on a logarithmic scale; (Middle) relative power discrepancy profile

\Delta S_{\text{rel}}(r)=\frac{\bar{S}_{\text{real}}(r)-\bar{S}_{\text{fake}}(r)}{\bar{S}_{\text{real}}(r)}\times 100\%

; (Right) kernel density estimation (KDE) of high-frequency spatial texture energy extracted via discrete Laplacian filtering.

Fig. 4: Multi-band spatial reconstructions via 2D Inverse DFT across representative radial bands (Bands 1, 3, 5, and 7): Row 1 displays authentic faces, and Row 2 displays manipulated faces.

Fig. 5: Targeted spatial-frequency forensics: (Top row, left-to-right) Cropped authentic input face, manipulated input face, Gaussian high-pass reconstructed authentic face, and high-pass reconstructed manipulated face; (Bottom row, left-to-right) 2D log-magnitude spectral difference ( $\log|F_{\text{real}}|-\log|F_{\text{fake}}|$ ), spatial residual heatmap ( $|I_{\text{HPF, real}}-I_{\text{HPF, fake}}|$ ), top 12% thresholded anomaly seams, and the resulting tampering localization overlay.

Model	AUC (%)
	FF++	Celeb-DF
Xception [ 19 ]	96.30	99.73
EfficientNet-B4 [ 20 ]	99.70	99.81
Multi-Att [ 21 ]	99.29	99.94
SPSL [ 22 ]	96.91	-
RECCE [ 23 ]	99.32	99.94

TABLE I: Comparison with SOTA on Intra-Dataset Analysis. The Metric used is Video Level AUC.

Model	CDF	WDF	DFDC	DFD
Xception [ 19 ]	61.80	62.72	48.98	87.86
EfficientNet-B4 [ 20 ]	64.29	63.83	-	-
Multi-Att [ 21 ]	67.44	59.74	-	-
SPSL [ 22 ]	76.88	-	66.16	-
RECCE [ 23 ]	68.71	64.31	69.06	-
FAce-X-Ray [ 24 ]	80.58	-	80.92	95.40

TABLE II: Cross-Domain Testing, Trained on FF++ c23 and tested on these Unseen Datasets (Video Level AUC (%))

Explore similar work

DYMAPIA: A Multi-Domain Framework for Detecting AI-based Video Manipulation
Apr 27, 2026Md Shohel Rana, Andrew H. SungDeepfake Detection Ai-Generated Video Detection
School of Computing Georgia Southern University Statesboro, GA 30460, USA · School of Computing Sciences & Computer Engineering The University of Southern Mississippi Hattiesburg, MS 39406, USA
Fractal Characterization of Low-Correlation Signals in AI-Generated Image Detection
Apr 19, 2026Wenwei Xie, Jie Yin, Lu Ma +2Deepfake Detection Ai-Generated Image Detection
Trend Micro Incorporated, Nanjing 210000, Jiangsu, China · Jiangsu Police Institute, Nanjing 210031, Jiangsu, China · BASF Incorporated, Nanjing 210000, Jiangsu, China +2
Ensemble Deep Learning Approaches for AI-Altered Video Detection
Jul 8, 2026Laiba Khan, Hung-Mao Wu, Wei Lin +3Ai-Generated Video Detection Deep Learning
Department of Mathematical and Computational Sciences, University of Toronto Mississauga · Department of Mathematical and Computational Sciences, University of Toronto

Apr 27, 2026, cs.CVJ/K move · Enter open · S save

DYMAPIA: A Multi-Domain Framework for Detecting AI-based Video Manipulation

Md Shohel Rana, Andrew H. Sung

School of Computing Georgia Southern University Statesboro, GA 30460, USA · School of Computing Sciences & Computer Engineering The University of Southern Mississippi Hattiesburg, MS 39406, USA

Deepfake Detection Ai-Generated Video Detection Dynawm

Open paper AskPDF arXiv

AI-generated media are advancing rapidly, raising pressing concerns for content authenticity and digital trust. We introduce DYMAPIA, a multi-domain Deepfake detection framework that fuses spatial, spectral, and temporal cues to capture subtle traces of manipulation in visual data. The system builds dynamic anomaly masks by combining evidence from Fourier spectra, local texture descriptors, edge irregularities, and optical flow consistency, which highlight tampered regions with fine spatial accuracy. These masks guide DistXCNet, a lightweight classifier distilled from Xception and optimized with depthwise separable convolutions for fast, region-focused classification. This joint design achieves state-of-the-art results, with accuracy and F1-scores exceeding 99% on FF++, Celeb-DF, and VDFD benchmarks, while keeping the model compact enough for real-time use. Beyond outperforming existing full-frame and multidomain detectors, DYMAPIA demonstrates deployment readiness for time-critical forensic tasks, including media verification, misinformation defense, and secure content filtering.

Abstract

Explore similar work

DYMAPIA: A Multi-Domain Framework for Detecting AI-based Video Manipulation

Fractal Characterization of Low-Correlation Signals in AI-Generated Image Detection

Ensemble Deep Learning Approaches for AI-Altered Video Detection