Devendra Ghori
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
State-of-the-art deepfake detectors achieve near-perfect in-domain accuracy yet degrade under crossgenerator 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 ε = 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2604.16486")
get_code_for_paper("2604.16486")
have("2604.16486")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2604.16486.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2604.16486)
Connect an agent — have() is free.