Architecture-Adaptive Uncertainty Fusion for Deepfake Detection

• URL: http://arxiv.org/abs/2606.06666v1
• Date: Thu, 04 Jun 2026 19:28:55 GMT
• Title: Architecture-Adaptive Uncertainty Fusion for Deepfake Detection
• Abstract summary: Deepfake detection systems achieve near-perfect accuracy on benchmarks, yet forensic deployment demands reliable prediction uncertainty.<n>We propose Correlation-d Fusion (COF), an architecture-adaptive framework that fuses five complementary uncertainty sources.<n>COF requires no model modifications and only 42 s of weight optimization, compared to 20--45 h for a 5-model Deep Ensemble.
• Score: 0.9940728137241215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Governed Human-AI Prioritization Under Uncertainty: Adaptive Estimation and Dependency-Constrained Portfolio Selection [0.0]
  AI-native software engineering increasingly combines human judgment, historical analogy, parametric estimation, and AI-generated forecasts inside the same prioritization decision.<n>We study five quantitative operators used in the D-POAF decision practice: Business Value Score (BVS), Effort and Risk Score (ERS), Prioritization Value Score (PVS), Collective Score (CCS), and Optimal Development Path (ODP)
  arXiv  Detail & Related papers  (2026-09-09T14:04:37Z)
• Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study [48.83701310501069]
  This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models.<n>We conduct a systematic empirical study of all $3 times 6 = 18$ combinations of six classifiers paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets.<n>Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across
  arXiv  Detail & Related papers  (2026-06-18T20:51:42Z)
• Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception [3.4563147061792527]
  This paper formally defines this pervasive vulnerability as the Hard-Category Reliability Problem (HCRP)<n>We propose Error-Decomposed Class-Conditional Fusion (ED-CCF), an elegant decision-layer inference framework.
  arXiv  Detail & Related papers  (2026-05-17T18:39:05Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty [12.261505821589452]
  We propose a single-pass method that estimates prediction uncertainty by measuring mutual information between decoder layers in segmentation networks.<n>RADMI achieves the highest correlation with deep ensemble uncertainty among all single-pass methods.<n>Our results suggest that linear aggregation of normalized information flow provides a principled and efficient proxy for prediction uncertainty in encoder-decoder architectures.
  arXiv  Detail & Related papers  (2026-05-02T15:49:25Z)
• Differentiable latent structure discovery for interpretable forecasting in clinical time series [38.473526928012724]
  We introduce StructGP, a continuous-time multi-task Gaussian process that couples differentiable structure learning to uncover a sparse, ordered directed acyclic graph (DAG) of inter-variable dependencies while preserving principled uncertainty.<n>We propose LP-StructGP, which augments StructGP with latent pathways-shared, temporally shifted trajectories inferred via subject-specific coupling filters and a softmax gating mechanism-to capture cross-patient progression patterns.
  arXiv  Detail & Related papers  (2026-04-30T14:59:50Z)
• Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models [2.064612766965483]
  We show five uncertainty quantification methods on MedGemma 4BIT across in distribution MIMIC CXR and outof distribution PadChest chest X ray datasets, with cross architecture validation on LLaVA RAD7B.<n>For well calibrated single model methods, predictive entropy from one forward pass predicts which samples will flip under rephrasing AUROC 0.711 on MedGemma, 0.878 on LLaVARAD p 10 4, enabling a single entropy threshold to flag both unreliable and sensitive predictions.
  arXiv  Detail & Related papers  (2026-04-10T04:18:47Z)
• Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments [0.0]
  We present a systematic study of a severe domain shift using a novel Gym2D dataset and the UCF101 dataset.<n>Our work challenges standard deployment assumptions, providing a principled safety analysis of both semantic and geometric skeleton recognition deployment.
  arXiv  Detail & Related papers  (2026-03-16T17:37:17Z)
• FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation [40.79057922854245]
  Federated image segmentation (RSIS) in federated environments has gained increasing attention.<n>We present FedEU, a framework for fine-tuning RSIS models driven by evidential uncertainty.
  arXiv  Detail & Related papers  (2026-03-08T05:11:03Z)
• Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis [3.4324137096523746]
  Chain-of-thought prompting enables Large Language Models to solve complex problems.<n>Existing methods suffer from poor calibration and severe overconfidence on incorrect predictions.<n>We propose Enhanced Dirichlet and Topology Risk (EDTR) to measure confidence across multiple reasoning paths.
  arXiv  Detail & Related papers  (2025-11-09T16:09:02Z)
• Accurate and Reliable Predictions with Mutual-Transport Ensemble [46.368395985214875]
  We propose a co-trained auxiliary model and adaptively regularizes the cross-entropy loss using Kullback-Leibler (KL) We show that MTE can simultaneously enhance both accuracy and uncertainty calibration. For example, on the CIFAR-100 dataset, our MTE method on ResNet34/50 achieved significant improvements compared to previous state-of-the-art method.
  arXiv  Detail & Related papers  (2024-05-30T03:15:59Z)
• MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers [41.56951365163419]
  "MixedNUTS" is a training-free method where the output logits of a robust classifier are processed by nonlinear transformations with only three parameters. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness.
  arXiv  Detail & Related papers  (2024-02-03T21:12:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.