2026 |
Brodarič, Marko; Ivanovska, Marija; Jain, Deepak Kumar; Peer, Peter; Štruc, Vitomir HCSI-Net: Hierarchical Cross-Stream Interaction for Generalizable Deepfake Detection Proceedings Article In: Proceedings of the International Workshop on Biometrics and Forensics (IWBF), pp. 1–6, 2026. Abstract | Links | BibTeX | Tags: CNN, deepfake, deepfake detection, deepfakes, transformer @inproceedings{IWBF2026,Deepfake detection is increasingly critical for multimedia forensics, yet many detectors degrade under distribution shifts caused by unseen generation pipelines, post-processing, and unconstrained capture conditions. To improve cross-dataset generalization, we propose a powerfull two-stream detector, named HCSI-Net, that couples a CNN and a transformer with progressive interaction during hierarchical feature extraction. The streams are linked via a novel bi-directional spatial cross-gating mechanism that jointly refines local texture cues and global contextual information across stages. The model is trained using manipulation-agnostic supervision based on simulated forgery artifacts and evaluated under challenging cross-dataset evaluation scenarios. Experiments across six widely used datasets demonstrate robust generalization across diverse deepfake generation techniques, achieving a macro-average AUC of 89.13 and consistently outperforming a number of strong state-of-the-art baselines. Ablation results confirm that intermediate cross-stream interaction drives the observed gains. |
2024 |
Brodarič, Marko; Peer, Peter; Struc, Vitomir Towards Improving Backbones for Deepfake Detection Proceedings Article In: Proceedings of ERK 2024, pp. 1-4, 2024. BibTeX | Tags: CNN, deep learning, deepfake detection, deepfakes, media forensics, transformer @inproceedings{ERK_2024_Deepfakes, |
2022 |
Dvoršak, Grega; Dwivedi, Ankita; Štruc, Vitomir; Peer, Peter; Emeršič, Žiga Kinship Verification from Ear Images: An Explorative Study with Deep Learning Models Proceedings Article In: International Workshop on Biometrics and Forensics (IWBF), pp. 1–6, 2022. Abstract | Links | BibTeX | Tags: biometrics, CNN, deep learning, ear, ear biometrics, kinear, kinship, kinship recognition, transformer @inproceedings{KinEars,The analysis of kin relations from visual data represents a challenging research problem with important real-world applications. However, research in this area has mostly been limited to the analysis of facial images, despite the potential of other physical (human) characteristics for this task. In this paper, we therefore study the problem of kinship verification from ear images and investigate whether salient appearance characteristics, useful for this task, can be extracted from ear data. To facilitate the study, we introduce a novel dataset, called KinEar, that contains data from 19 families with each family member having from 15 to 31 ear images. Using the KinEar data, we conduct experiments using a Siamese training setup and 5 recent deep learning backbones. The results of our experiments suggests that ear images represent a viable alternative to other modalities for kinship verification, as 4 out of 5 considered models reach a performance of over 60% in terms of the Area Under the Receiver Operating Characteristics (ROC-AUC). |