Architecture-Adaptive Uncertainty Fusion for Deepfake Detection
Quick Answer
The proposed Correlation-Optimized Fusion (COF) framework enhances deepfake detection by fusing five uncertainty sources, achieving better performance than Random Forest in 9 out of 11 architectures.
Quick Take
The proposed Correlation-Optimized Fusion (COF) framework enhances deepfake detection by fusing five uncertainty sources, achieving better performance than Random Forest in 9 out of 11 architectures. COF requires only 42 seconds for weight optimization, significantly less than the 20-45 hours for a 5-model Deep Ensemble, while maintaining robustness against distribution shifts.
Key Points
- COF fuses epistemic, aleatoric, calibration, conformal, and distributional uncertainties.
- Achieves 7.3x higher correlation than Random Forest in specific architectures.
- Demonstrates a 90.7% degradation in correlation across datasets.
- Requires no model modifications, optimizing weights in just 42 seconds.
- Identifies domain-adaptive uncertainty quantification as a key challenge.
Article Content
From source RSS / original summaryarXiv:2606. 06666v1 Announce Type: new Abstract: Deepfake detection systems achieve near-perfect accuracy on benchmarks, yet forensic deployment demands reliable prediction uncertainty. Existing uncertainty quantification (UQ) methods rely on single sources and ignore that optimal uncertainty composition varies across architectures.
We propose Correlation-Optimized Fusion (COF), an architecture-adaptive framework that fuses five complementary uncertainty sources -- epistemic, aleatoric, calibration, conformal, and distributional -- by maximizing Pearson correlation between fused uncertainty scores and prediction errors via constrained optimization on the probability simplex. COF requires no model modifications and only 42 s of weight optimization, compared to 20--45 h for a 5-model Deep Ensemble.
Evaluation across eleven architectures on FaceForensics++ reveals a fundamental trade-off: under matched train/evaluation protocol, non-linear methods achieve approximately 5--6% higher in-domain correlation than COF (mean r = 0. 438), but this reverses under distribution shift. On CelebDF, COF outperforms Random Forest in 9/11 architectures with up to 7. 3x higher correlation (MaxViT-B: r = 0. 249 vs. 0. 034); RF degrades 85% cross-domain to r = 0.
071, whereas COF retains substantially more signal (74% drop to r = 0. 116). Cross-dataset evaluation on CelebDF and DFDC reveals catastrophic generalization failure across all methods: in-domain correlations of 0. 41--0. 47 collapse to near-zero externally (mean degradation 90. 7%), with seven of eleven architectures exhibiting uncertainty inversion.
These results establish COF as a practical, interpretable framework for controlled-distribution deployment and identify domain-adaptive UQ as the central open challenge for forensic deployment.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.
