The paper introduces FADNet, a face authenticity detector that treats forgery detection as a one‑class classification problem, training only on authentic faces. It uses Evidential Deep Learning to measure uncertainty and a pseudo‑forgery generator to sharpen decision boundaries. Experiments on DF40 and ASFD show FADNet surpasses state‑of‑the‑art methods with 96.63% accuracy and 98.83% precision.
By Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu, Zhenxing Qian, Xinpeng Zhang, Zaiwang Gu
arXiv:2411. 19715v4 Announce Type: replace-cross Abstract: We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector.
By Xinjie Cui, Yuezun Li, Delong Zhu, Jiaran Zhou, Junyu Dong, Siwei Lyu
The paper introduces Separable Prompt Learning (SePL), a method that enhances face forgery detection by leveraging CLIP’s textual encoder through two separate learnable prompts. SePL incorporates a cross-modality alignment strategy and specific objectives to distill forgery knowledge from CLIP. Experiments show that SePL outperforms existing approaches in cross-dataset and cross-method evaluations.
By Enrui Yang, Baoyuan Wu, Yuezun Li
arXiv:2608. 06865v1 Announce Type: cross Abstract: The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety.
By Xuechao Zou, Shun Zhang, Kai Li, Yi Zhou, Xinyu Sun, Yuhui Chen, Zhe Wu, Congyan Lang, Junliang Xing
FORGE is a forensic deepfake analysis system that provides region‑grounded natural language explanations for image manipulations. It addresses the inductive bias mismatch of multimodal large language models by adding a Vision‑Only Model trained on dense patch prediction, allowing the language model to interleave tokens with preserved spatial correspondence. Across face‑manipulated and fully synthetic content, FORGE delivers fine‑grained attribute queries and outperforms in‑domain baselines, with region‑specific evaluation and human studies confirming explanation faithfulness.
By Rohit Kundu, Shan Jia, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury
arXiv:2609.01511v1 Announce Type: new
Abstract: Face forgery detectors often achieve strong results on controlled benchmarks, but their reliability under realistic image degradations remains limited....
By Lucas Cunha, Lucas Sotomaior, Lucas Gasperin, Beatriz Caldas, Eduardo Pianovski, Rayson Laroca
arXiv:2610.29442v1 Announce Type: new
Abstract: Recent advances in generative models have enabled highly realistic face forgeries, yet generalizing deepfake detectors to unseen manipulation pipelines...
By Chao Shuai, Shaojing Fan, Kun Pan, Jinwu Hu, Weichen Lian, Ziqi Yang, Zhongjie Ba, Zhenguang Liu
arXiv:2605. 09089v2 Announce Type: replace-cross Abstract: Digital onboarding and eKYC systems used by banks, fintech platforms, telecom providers, and other third-party services commonly verify users by comparing an uploaded identity document with a selfie or live facial capture.
By Abhishek Kumar, Riya Tapwal, Carsten Maple, Mark Hooper
The paper presents lightweight architectures for detecting GAN-generated synthetic faces, comparing a compact Swin Transformer, pre‑trained Swin‑Tiny and Swin‑Small models, and a hybrid EfficientNet‑B0 + Swin Transformer. Using the 140K Real and Fake Faces dataset, the hybrid model achieved 99% accuracy and 99.44% recall on 5,000 test images, outperforming both pure Swin variants and a CNN‑only baseline. The study demonstrates that combining hierarchical CNN features with shifted‑window self‑attention yields an efficient, computationally lightweight detection method.
By Sejuti Basu, Ashima Sood, Vijay Kumar, Sahil Sharma
The paper presents an explainable deep‑learning workflow for detecting deepfake images, comparing a compact convolutional model trained from scratch with a fine‑tuned ImageNet‑pretrained MobileNetV2 model. Using a balanced dataset of 140,000 real and fake faces, the pretrained model achieved 95.90% accuracy, outperforming the from‑scratch model’s 84.15% accuracy. Gradient‑weighted class activation mapping (Grad‑CAM) was employed to highlight image regions influencing predictions, and a Flask prototype was built for side‑by‑side inspection.
By Saad Korchi, Abderrahim Waga
arXiv:2608.29802v1 Announce Type: new
Abstract: Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Pre...
By Hatef Otroshi Shahreza, Asif Hussain Khan, Peter Lorenz, Alain Komaty, S\'ebastien Marcel
This paper presents an interpretable deepfake detection framework that explicitly encodes physically grounded forensic cues to analyze spatially and temporally coherent facial features in video sequences. The method transforms videos into identity-consistent facial trajectories, segments them into fixed-length temporal windows, and represents each frame with 68 structured descriptors across photometric, textural, geometric, and compression domains. These descriptors are processed by an LSTM to capture temporal dependencies, achieving strong F1-scores on four benchmark datasets and demonstrating robust cross-dataset generalization.
By Chahira Benhama, Mohand Sa\"id Allili, Assia Hamadene