Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System

• URL: http://arxiv.org/abs/2607.13234v1
• Date: Tue, 14 Jul 2026 19:53:09 GMT
• Title: Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System
• Abstract summary: Deepfake detectors that achieve near-perfect scores on academic benchmarks collapse on real-world content.<n>We argue this gap is structural: static detectors are trained once against a moving generative frontier.<n>We present BitMind Forensics (BMF), trained through Bittensor SN34, an open adversarial competition that continually refreshes the training distribution.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deepfake detectors that achieve near-perfect scores on academic benchmarks collapse on real-world content: recent in-the-wild evaluations report AUC drops of 45-50% for state-of-the-art open-source models. We argue this gap is structural: static detectors are trained once against a moving generative frontier. We present BitMind Forensics (BMF), trained through Bittensor SN34, an open adversarial competition that continually refreshes the training distribution. We evaluate one dated export comprising image, general-video, and human-video checkpoints across nineteen public datasets: the canonical face-swap suites (FaceForensics++, Celeb-DF v1/v2/++, DFDC, DFD, UADFV, DF40) and recent in-the-wild and AI-generated-media benchmarks (Sumsub, Deepfake-Eval-2024, WildRF, Community Forensics, AIGCDetectBench, GenImage, AI-GenBench, AIGIBench, RAID, GenVidBench, GenVideo-100K). BMF reaches 0.936 AUC on Sumsub's original images and 0.872 pooled AUC over its full four-condition manipulation battery (1.4M images), staying robust under perturbation (0.855 JPEG, 0.799 downscaled), while GPEN enhancement improves detection (0.996). On Deepfake-Eval-2024, it matches the best commercial detector on images (0.915 vs 0.90) and exceeds it on video (0.822 vs 0.79), far above the best open-source detectors (0.56 and 0.63). It reaches 0.991 AUC on a 21-generator AI-image panel and 0.918 on GenVidBench, and exceeds the FF++-trained frontier on DFDC (0.947 vs 0.843) and Celeb-DF v2 (0.9985 vs 0.956), both contamination-audited, with statistical parity on Celeb-DF++. In a temporal study, successive dated exports improve on held-out media from generators absent from the static baseline's training (image 0.842 to 0.902; video 0.864 to 0.936). Our evaluation harness is public, and at publication the production API serves the exact evaluated snapshot for independent verification.

Related papers

• Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection [0.0]
  Automated "suspicious behavior" flagging is a headline promise of AI surveillance.<n>Field reports high frame-level ROC-AUC on standard video anomaly detection benchmarks.<n>We audit what happens when that assumption is dropped.
  arXiv  Detail & Related papers  (2026-06-28T17:08:02Z)
• Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals [0.0]
  We release an open-source object detection model for 31 classes, 28 common UK mammal and bird species, plus utility classes for humans, calibration poles, and vehicles.<n>The model achieves a mean Average Precision of 0.984 at Intersection over Union (IoU) of 0.5 (0.956 at IoU 0.5-0.95) on the held-out validation set.<n>We release the trained weights in ONNX format under a non-commercial licence, with local desktop and real-time camera support.
  arXiv  Detail & Related papers  (2026-06-09T14:47:24Z)
• Intermediate Representations are Strong AI-Generated Image Detectors [51.7378156094049]
  We propose a search-based method employing data sensitivity embedding in intermediate layers to detect AI-generated images.<n>Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity.<n>Our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.
  arXiv  Detail & Related papers  (2026-05-05T23:26:02Z)
• Comparison of Multiple Classifiers for Android Malware Detection with Emphasis on Feature Insights Using CICMalDroid 2020 Dataset [0.0]
  Signature scanners lagged behind fast release cycles on public app stores.<n>We used CICMalDroid PCA2020, which contained 17,341 apps across Benign, Banking, SMS malware, and Riskware.<n> gradient boosting on the original features performed best.
  arXiv  Detail & Related papers  (2026-01-20T04:50:58Z)
• Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification [71.06194656633447]
  We establish an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set. UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images.
  arXiv  Detail & Related papers  (2023-04-08T10:47:41Z)
• Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification [52.77024349608834]
  To investigate chest radiograph (CXR) classification performance of vision transformers (ViT) and interpretability of attention-based saliency. ViTs were fine-tuned for lung disease classification using four public data sets: CheXpert, Chest X-Ray 14, MIMIC CXR, and VinBigData. ViTs had comparable CXR classification AUCs compared with state-of-the-art CNNs.
  arXiv  Detail & Related papers  (2023-03-03T12:05:41Z)
• The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations [59.48245489413308]
  We developed and tested a COVID-19 rapid prescreening model using the eye-region images captured in China and Spain with cellphone cameras. The performance was measured using area under receiver-operating-characteristic curve (AUC), sensitivity, specificity, accuracy, and F1.
  arXiv  Detail & Related papers  (2021-09-18T02:28:01Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)
• Semi-supervised learning for generalizable intracranial hemorrhage detection and segmentation [0.0]
  We develop and evaluate a semisupervised learning model for intracranial hemorrhage detection and segmentation on an outofdistribution head CT evaluation set. An initial "teacher" deep learning model was trained on 457 pixel-labeled head CT scans collected from one US institution from 2010-2017. A second "student" model was trained on this combined pixel-labeled and pseudo-labeled dataset.
  arXiv  Detail & Related papers  (2021-05-03T00:14:43Z)
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery [56.10033255997329]
  We propose a novel deep learning method based on a Convolutional Neural Network (CNN) It simultaneously detects and geolocates plantation-rows while counting its plants considering highly-dense plantation configurations. The proposed method achieved state-of-the-art performance for counting and geolocating plants and plant-rows in UAV images from different types of crops.
  arXiv  Detail & Related papers  (2020-12-31T18:51:17Z)
• Automatic classification of multiple catheters in neonatal radiographs with deep learning [2.256008196530956]
  We develop and evaluate a deep learning algorithm to classify multiple catheters on neonatal chest and abdominal radiographs. A convolutional neural network (CNN) was trained using a dataset of 777 neonatal chest and abdominal radiographs.
  arXiv  Detail & Related papers  (2020-11-14T21:27:21Z)

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.