IEEE transactions on biometrics, behavior, and identity science最新文献

{"title":"OU-CA: A Face–Voice Multimodal Benchmark for Continuous User Authentication","authors":"Xiang Li;Chi Xu;Yasushi Yagi","doi":"10.1109/TBIOM.2026.3690283","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3690283","url":null,"abstract":"Unlike conventional login authentication systems, which verify a user’s identity only once at the beginning of a session, continuous authentication enhances security by continuously verifying the user throughout the session. In this paper, we introduce a novel multimodal face-voice benchmark dataset for continuous user authentication. It contains data from 1,169 subjects, collected through web-based conversational games conducted between paired participants. During the games, participants’ facial videos and corresponding voice data were automatically recorded. Specifically, five cameras surrounding the display captured faces from different viewing angles to increase pose variations. Moreover, we provide baseline evaluations using state-of-the-art face and speaker recognition methods on our database. We further propose a novel disentanglement cluster network for continuous face authentication, achieving state-of-the-art performance on both our database and the widely used IJB-B and IJB-C datasets. We expect that our database will facilitate further research on continuous authentication and the development of more secure authentication systems.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"880-891"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11505915","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AudioAuth: A Dual-Watermarking Framework for Robust Audio Integrity and Source Attribution","authors":"Aditya Pujari;Ajita Rattani","doi":"10.1109/TBIOM.2026.3679274","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3679274","url":null,"abstract":"Voice biometric systems face escalating threats from neural speech synthesis technologies capable of producing speaker-indistinguishable audio. Existing audio watermarking defenses remain vulnerable to spectral-domain attacks, offer only coarse tamper localization, and often degrade under codec compression. We propose AudioAuth, a dual-watermarking framework for joint content integrity verification and source attribution in voice biometric security, extending our prior single-channel work WaveVerify. AudioAuth employs a frequency-partitioned dual-channel encoding strategy: a fixed model identifier embedded in even frequency bands enables reliable source attribution, while a dynamic payload embedded in odd bands supports fine-grained temporal tamper localization. A dynamic effect scheduler further enables co-adaptive training, improving robustness against adversarial distortions and signal transformations. Evaluated against six state-of-the-art baselines spanning signal-level (AudioSeal, WavMark, WaveVerify) and representation-level (WMCodec, Timbre, DiscreteWM) approaches, AudioAuth achieves precise temporal localization (MIoU = 0.983), accurate multi-source TTS attribution (98.8% across eight systems), and negligible impact on speaker verification performance (EER increase of only 0.07%).","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"680-694"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial for the TBIOM Special Issue on The Best Reviewed Papers From IJCB 2025","authors":"Lale Akarun;Koichi Ito;Karthik Nandakumar;Vitomir Štruc;Xiangyu Zhu;Mark Nixon","doi":"10.1109/TBIOM.2026.3724304","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3724304","url":null,"abstract":"","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"678-679"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11691260","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards Trustworthy Biometrics: Generalized Detection of Diffusion-Generated Fingerprint Forgeries in Partial Scenarios","authors":"Mao-Hsiu Hsu;Yung-Ching Hsu;Ching-Te Chiu","doi":"10.1109/TBIOM.2026.3683085","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3683085","url":null,"abstract":"Fingerprint recognition is widely used for biometric authentication, yet it is increasingly vulnerable to unauthorized access with the rapid advancement of generative artificial intelligence. In particular, Generative Adversarial Networks (GANs) and diffusion models enable highly realistic fingerprint forgeries, posing serious security threats to fingerprint based systems. Developing deep forgery detection methods that generalize to unseen generative models is therefore critical, especially for partial fingerprints captured by side mounted sensors on smartphones and Artificial Intelligence of Things (AIoT) devices, where limited ridge information constrains discriminative features. Existing approaches often rely on extensive multi generator training or suffer from limited robustness against diffusion based attacks and poor generalization in multi generative model scenarios. In this work, we propose Multi Generative Models Fingerprint Forgery Detection, a generalized framework for partial fingerprint forgery detection that supports both single generative model (SGM) and multi generative models (MGM) training against GAN and Diffusion based attacks. The proposed method introduces four training only modules to enhance feature generalization without increasing inference complexity. By integrating local and global representations, suppressing identity dependent information, and expanding forgery feature distributions through feature augmentation and multi classifier learning, the framework improves robustness to diverse generative attacks, particularly unseen diffusion based forgeries. Experimental results show that under SGM training, the proposed method achieves an average accuracy of 88.57%, outperforming UniversalFakeDetect by 3.33% with a <inline-formula> <tex-math>$17.82times $ </tex-math></inline-formula> faster inference speed. Under MGM training, accuracy improves to 91.11% with two generative models and further reaches 92.47% with three models, while maintaining a lightweight inference time of 0.0161 seconds per image, demonstrating strong generalization across diverse generators and strong potential for edge and AIoT deployment. The source code will be publicly available at: <uri>https://github.com/Maohsiuhsu/Towards-Trustworthy-Biometrics-Generalized-Detectionof-Diffusion-Generated-Fingerprint-.git</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"857-869"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion Model With Perceptual Similarity Fusion for Unsupervised Fingerphoto Presentation Attack Detection","authors":"Hailin Li;Raghavendra Ramachandra;Narayan Vetrekar;R. S. Gad","doi":"10.1109/TBIOM.2026.3674393","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3674393","url":null,"abstract":"The rapid advancement of premium smartphones with sophisticated high resolution cameras has enabled reliable and convenient contactless acquisition of fingerprint biometrics, making them suitable for verification at scale. However, as with other biometric systems, contactless fingerprint verification remains vulnerable to presentation attacks. Many Presentation Attack Detection (PAD) methods rely on supervised learning that requires labelled attack data, which limits generalisation. We propose an unsupervised PAD approach based on the Denoising Diffusion Probabilistic Model (DDPM). The system is trained only on bona fide samples and makes decisions via score level fusion of two deep similarity measures, yielding robustness to unseen attacks without access to attack labels. We further provide a Jacobian based theoretical analysis that explains why diffusion reconstructions are well suited to PAD. Using Frobenius and spectral norms together with a log determinant surrogate, we show that the iterative refinement in diffusion models preserves ridge aligned structure while contracting off manifold artifacts, thereby accounting for the observed empirical gains over single shot alternatives. In addition, we introduce a new fingerphoto presentation attack dataset comprising 101 subjects with 6,060 bona fide and 1,818 attack images captured on recent smartphones under diverse conditions. Benchmarking across four datasets shows that the proposed method is effective in practice, improving PAD performance and outperforming strong supervised baselines and recent state of the art methods in unseen attack scenarios. We report uncertainty estimates and non parametric statistical summaries across datasets and PAIs (Presentation Attack Instruments), which indicate consistent advantages without significant regressions, supporting the suitability of diffusion based PAD for deployment.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"831-846"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Psychophysically Guided Training for Fingerprint Presentation Attack Detection","authors":"Samuel Webster;Walter Scheirer;Adam Czajka","doi":"10.1109/TBIOM.2026.3664679","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3664679","url":null,"abstract":"Psychophysically-guided training, which directs model learning based on human-perceptual annotations, has demonstrated generalization improvements across various vision tasks, including biometric presentation attack detection (PAD). In saliency-guided training, model’s decision-making is aligned to image regions marked by human annotators. In perceptually-weighted training, human psychophysical measurements weigh per-sample loss, prioritizing samples with greater ‘difficulty’. This paper presents the first application of both strategies to fingerprint PAD. We conducted a 50-participant study to perceptually annotate 800 fingerprint samples, producing human-sourced saliency maps and annotation-duration-based perceptual weighting coefficients. These are utilized alongside algorithmically-generated “pseudosaliency” (minutiae-based, quality-based, and autoencoder-generated) and additional perceptual weighting coefficients derived from minutiae count and sample quality. Evaluating on the 2021 Fingerprint Liveness Detection Competition testing set, we explore various configurations within nine distinct training scenarios to assess the impact of psychophysically-guided training on accuracy and generalization. Our findings demonstrate the effectiveness of psychophysically-guided training for fingerprint PAD in both limited and large data contexts, and we present multiple configurations capable of earning the first place on the LivDet-2021 benchmark. Our results highlight psychophysically-guided training’s promise for increased model generalization capabilities, its effectiveness when data is limited, and its potential to scale to larger datasets in fingerprint PAD. All collected saliency maps, perceptual weighting coefficient sets, and trained models are released with the paper to support reproducible research.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"707-717"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Motion-Aware Spatio-Temporal Networks for Dynamic Gesture Recognition on Point Clouds","authors":"Qiuxia Wu;Xinran Xie;Sangni Xu;Wenxiong Kang","doi":"10.1109/TBIOM.2026.3695284","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3695284","url":null,"abstract":"Biometric authentication based on dynamic hand gestures has attracted increasing attention due to its integration of both physiological and behavioral traits. Among various approaches, point cloud–based dynamic gesture recognition has emerged as a particularly promising direction, owing to its ability to preserve rich 3D geometric information. However, existing methods still struggle to effectively model point-level motion features while capturing overall temporal dynamics, which limits their ability to extract fine-grained motion information from point cloud sequences. To address these challenges, we first propose a point cloud–based dynamic gesture recognition framework, termed Motion-Temporal Network (MoTeNet). MoTeNet explicitly models cross-frame point-wise motion, enabling enhanced fine-grained dynamic perception and effective extraction of point-level motion features, thereby achieving strong recognition performance. Nevertheless, this explicit motion modeling paradigm relies on multi-stage feature extraction and fusion, and requires repeated neighborhood searches across adjacent frames, resulting in high computational complexity. To further improve efficiency, we propose the Implicit Spatio-Temporal Network (ISTNet), which adopts a novel motion modeling strategy. Specifically, ISTNet constructs a cross-frame neighborhood structure during spatial feature learning, allowing motion information to be seamlessly integrated into spatial representations through local feature aggregation. This design enables implicit motion encoding while effectively avoiding the additional computational overhead introduced by explicit motion modeling. In addition, a Saliency-Aware Motion Encoder (SAME) is introduced to capture complementary global motion representations, further enhancing the modeling of holistic dynamic patterns. Extensive experiments on three public benchmarks, including SHREC’17, DHG, and NVGesture, demonstrate that the proposed methods achieve state-of-the-art performance in terms of both recognition accuracy and computational efficiency. Ablation studies further validate the effectiveness of the proposed framework.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"769-779"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward Fully Automated ISO/ICAO Face Compliance Verification via Prompt Learning","authors":"Nicoló Di Domenico;Guido Borghi;Annalisa Franco;Davide Maltoni","doi":"10.1109/TBIOM.2026.3685805","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3685805","url":null,"abstract":"Ensuring that facial images conform to widely adopted quality guidelines is a crucial step in optimizing the document enrollment workflow, which includes the face verification task. In this paper, we focus on the ISO/ICAO standard, which defines the requirements for facial photographs used in official documents, such as passports, ensuring consistency in face quality and thereby improving reliable recognition by both humans and biometric systems. Generally, ISO/ICAO compliance verification is manually performed through a slow, subjective, and non-scalable process, then to address these challenges, we introduce a fully automated system that assesses face compliance directly from the official standard requirements, eliminating dependence on predefined, hand-crafted features and empirically set thresholds. The method integrates a language model with an innovative prompt learning strategy and a contrastive learning paradigm to assess whether a given facial image satisfies specific quality criteria. Experimental evaluations demonstrate that our method achieves competitive accuracy compared to both academic and commercial baselines. By facilitating the integration and maintenance of compliance regulations, the proposed framework offers a practical, scalable, and regulation-centric solution for automated image quality verification. All code and models are publicly available <uri>https://github.com/MI-BioLab/CLIP-ICAO-Compliance</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"730-740"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11488644","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Keystroke-Aligned Body Motion Patterns for Short-Burst Continuous Smartphone Authentication: A Proof-of-Concept Study Using Motion Capture","authors":"Nicholas Cariello;Lam Nguyen;Rosemary Gallagher;Isaac Kurtzer;Kiran S. Balagani;Paolo Gasti","doi":"10.1109/TBIOM.2026.3674400","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3674400","url":null,"abstract":"Continuous smartphone user authentication systems aim to verify a user’s identity by monitoring behavioral patterns during typical device usage. Current approaches based on keystroke dynamics have demonstrated robust performance over extended authentication windows ranging from 20 to 120 seconds, with recent advances reducing these requirements to 5–10 seconds. However, many common smartphone interactions, such as typing a URL in a mobile browser, entering search queries on the home screen, or composing brief text message responses, occur in very short bursts lasting only 1–2 seconds. Consequently, the current state of the art in smartphone keystroke dynamics remains unsuitable for authenticating users during these prevalent short-burst textual interactions. Building upon our previous research that demonstrated the effectiveness of integrating body motion features with swipe-based behavioral biometrics, this proof of concept study explores whether similar performance enhancements can be achieved for keystroke dynamics within short authentication windows. We investigate a multimodal approach that combines traditional keystroke dynamics with laboratory-grade 3D motion capture body movement data and smartphone motion features, utilizing keystroke events as temporal anchors for feature extraction. We evaluate our methodology on our publicly available dataset comprising of 42 users and demonstrate that the integration of phone motion and body motion features with keystroke dynamics achieves an equal error rate (EER) of 1.5% over 1-second authentication windows when utilizing all available features. This represents a substantial improvement over keystroke-only approaches, which typically achieve EERs of 9.5% to 11.9% under similar conditions. Additionally, we identify the specific body regions and feature types most valuable for short-window authentication, providing a roadmap for future implementations using smartphone sensors and wearable devices.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"817-830"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Doubly Relaxed Knowledge Distillation for Deep Face Recognition","authors":"Si Zhou;Xiaochen Yuan;Guanghua Yang;Xinyuan Zhang;Zuobin Ying;Xueyuan Gong","doi":"10.1109/TBIOM.2026.3671881","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3671881","url":null,"abstract":"In face recognition tasks, knowledge distillation tends to employ feature-based methods due to their better performance, while neglecting further research on logits-based distillation methods. However, the former strictly requires consistent feature dimensions between the teacher and student, which calls for additional design work. In this paper, we find that most logits-based methods not only strictly constrain the logits variances of the teacher and student to be consistent, but also implicitly involve a restricted linear relationship. Therefore, we propose a new logits-based distillation method, named Doubly Relaxed Knowledge Distillation (DR-KD). Specifically, we use Z-score standardization instead of the softmax function to process logits, and achieve consistent logits variances through manual intervention. Subsequently, we introduce cosine similarity to measure the knowledge transfer between teacher and student networks. Through derivation, we find that the Pearson coefficient can be directly and equivalently used to calculate the similarity between their original logits. The linear relationship represented by the Pearson coefficient is more extensive, and the restricted linear relationship is a special case of it. Our method can break the constraint on variance consistency and relax the restriction on linear relationships. As a result, extensive experiments and ablation studies show that our DR-KD can enhance the discriminative learning capability of the student and demonstrate superiority over various state-of-the-art competitors on several face challenging benchmarks, such as IJB-B, IJB-C, and so on.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"805-816"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}