cs.CVApr 13, 2026

Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection

Authors: Devendra Ghori

Organizations: Researcher, Aletheia Project

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

State-of-the-art deepfake detectors achieve near-perfect in-domain accuracy yet degrade under cross-generator shifts, heavy compression, and adversarial perturbations. The core limitation remains the decoupling of semantic artifact learning from physical invariants: optical-flow discontinuities, specular-reflection inconsistencies, and cardiac-modulated reflectance (rPPG) are treated either as post-hoc features or ignored. We introduce PhyLAA-X, a novel physics-conditioned extension of Localized Artifact Attention (LAA-X). PhyLAA-X injects three end-to-end differentiable physics-derived feature volumes - optical-flow curl, specular-reflectance skewness, and spatially-upsampled rPPG power spectra - directly into the LAA-X attention computation via cross-attention gating and a resonance consistency loss. This forces the network to learn manipulation boundaries where semantic inconsistencies and physical violations co-occur - regions inherently harder for generative models to replicate consistently. PhyLAA-X is embedded across an efficient spatiotemporal ensemble (EfficientNet-B4+BiLSTM, ResNeXt-101+Transformer, Xception+causal Conv1D) with uncertainty-aware adaptive weighting. On FaceForensics++ (c23), Aletheia reaches 97.2% accuracy / 0.992 AUC-ROC; on Celeb-DF v2, 94.9% / 0.981; on DFDC, 90.8% / 0.966 - outperforming the strongest published baseline (LAA-Net [1]) by 4.1-7.3% in cross-generator settings and maintaining 79.4% accuracy under epsilon = 0.02 PGD-10 attacks. Single-backbone ablations confirm PhyLAA-X alone delivers a 4.2% cross-dataset AUC gain. The full production system is open-sourced at https://github.com/devghori1264/Aletheia (v1.2, April 2026) with pretrained weights, the adversarial corpus (referred to as ADC-2026 in this work), and complete reproducibility artifacts.

Figures & tables

Figure 1: Overall Architecture of Aletheia.
Figure 2: Detailed PhyLAA-X Module.
Figure 3: Example PhyLAA-X-Enhanced GradCAM++ Visualization.
MethodFF++ c23FF++ c40Celeb-DFDFDCWildDeepfakeAvg. Cross
Xception baseline0.9790.9420.9650.9410.8120.890
LAA-Net [ 1 ]0.9870.9580.9720.9550.8410.919
DF40 baseline [ 2 ]0.9900.9500.9750.9600.8530.927
Aletheia (Ours)0.9920.9680.9810.9660.8890.951
Table 1: In-domain and cross-dataset performance (AUC-ROC).
Attack ( ε=0.02\varepsilon=0.02 )Undefended Acc+Input Trans.+PhyLAA-X OnlyFull Aletheia
FGSM48.7%71.2%76.4%82.1%
PGD-1041.2%65.9%73.8%79.4%
Transfer———74.6%
Table 2: Adversarial robustness ( ε=0.02\varepsilon=0.02 ).
Figure 4: Ablation Bar Chart – Cross-Dataset AUC Gain.
More in this topic

Deepfake Detection

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

See all 241 papers

Explore similar work

CardsList
Apr 5, 2026

LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection

In this paper, we propose Localized Artifact Attention X (LAA-X), a novel deepfake detection framework that is both robust to high-quality forgeries and capable of generalizing to unseen manipulations. Existing approaches typically rely on binary classifiers coupled with implicit attention mechanisms, which often fail to generalize beyond known manipulations. In contrast, LAA-X introduces an explicit attention strategy based on a multi-task learning framework combined with blending-based data synthesis. Auxiliary tasks are designed to guide the model toward localized, artifact-prone (i.e., vulnerable) regions. The proposed framework is compatible with both CNN and transformer backbones, resulting in two different versions, namely, LAA-Net and LAA-Former, respectively. Despite being trained only on real and pseudo-fake samples, LAA-X competes with state-of-the-art methods across multiple benchmarks. Code and pre-trained weights for LAA-Net\footnote{https://github.com/10Ring/LAA-Net} and LAA-Former\footnote{https://github.com/10Ring/LAA-Former} are publicly available.

Dat Nguyen, Enjie Ghorbel, Anis Kacem +2

CVI2, SnT, University of Luxembourg, Luxembourg · CRISTAL laboratory, ENSI, University of Manouba, Tunisia · SnT, University of Luxembourg, Luxembourg

Deepfake DetectionImage Forgery Localization
AskPDF
Mar 2, 2026

Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection

The rapid advancement of deepfake generation techniques poses significant threats to public safety and causes societal harm through the creation of highly realistic synthetic facial media. While existing detection methods demonstrate limitations in generalizing to emerging forgery patterns, this paper presents Deepfake Forensics Adapter (DFA), a novel dual-stream framework that synergizes vision-language foundation models with targeted forensics analysis. Our approach integrates a pre-trained CLIP model with three core components to achieve specialized deepfake detection by leveraging the powerful general capabilities of CLIP without changing CLIP parameters: 1) A Global Feature Adapter is used to identify global inconsistencies in image content that may indicate forgery, 2) A Local Anomaly Stream enhances the model's ability to perceive local facial forgery cues by explicitly leveraging facial structure priors, and 3) An Interactive Fusion Classifier promotes deep interaction and fusion between global and local features using a transformer encoder. Extensive evaluations of frame-level and video-level benchmarks demonstrate the superior generalization capabilities of DFA, particularly achieving state-of-the-art performance in the challenging DFDC dataset with frame-level AUC/EER of 0.816/0.256 and video-level AUC/EER of 0.836/0.251, representing a 4.8% video AUC improvement over previous methods. Our framework not only demonstrates state-of-the-art performance, but also points out a feasible and effective direction for developing a robust deepfake detection system with enhanced generalization capabilities against the evolving deepfake threats. Our code is available at https://github.com/Liao330/DFA.git

Jianfeng Liao, Yichen Wei, Raymond Chan Ching Bon +3

Shenzhen Technology University, Guangdong, China · Singapore Institute of Technology, Singapore, Singapore · The University of Hong Kong, Hong Kong, China +1

Deepfake DetectionDigital Image ForensicsVLM Adaptation
AskPDF
Mar 9, 2026

X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection

The surge of highly realistic synthetic videos produced by contemporary generative systems has significantly increased the risk of malicious use, challenging both humans and existing detectors. Against this backdrop, we take a generator-side view and observe that internal cross-attention mechanisms in these models encode fine-grained speech-motion alignment, offering useful correspondence cues for forgery detection. Building on this insight, we propose X-AVDT, a robust and generalizable deepfake detector that probes generator-internal audio-visual signals accessed via DDIM inversion to expose these cues. X-AVDT extracts two complementary signals: (i) a video composite capturing inversion-induced discrepancies, and (ii) an audio-visual cross-attention feature reflecting modality alignment enforced during generation. To enable faithful cross-generator evaluation, we further introduce MMDF, a new multimodal deepfake dataset spanning diverse manipulation types and rapidly evolving synthesis paradigms, including GANs, diffusion, and flow-matching. Extensive experiments demonstrate that X-AVDT achieves leading performance on MMDF and generalizes strongly to external benchmarks and unseen generators, outperforming existing methods with accuracy improved by 13.1%. Our findings highlight the importance of leveraging internal audio-visual consistency cues for robustness to future generators in deepfake detection.

Youngseo Kim, Kwan Yun, Seokhyeon Hong +3

Visual Media Lab, KAIST

Deepfake DetectionAudio Deepfake Detection
AskPDF