Deepfakes leverage artificial intelligence to generate highly realistic but falsified visual content, raising concerns for security and trust in digital media. Detecting such manipulations becomes more challenging when videos are compressed, as compression algorithms introduce artifacts that obscure forensic evidence. One possible solution is to train separate models for different compression levels; however, this approach increases computational costs and limits scalability. To address this challenge, we introduce a unified framework designed to improve robustness against varying degrees of video compression. Our approach combines (i) a dedicated MPEG-based augmentation strategy tailored for compressed videos, and (ii) two architectural designs named Multi-Head (MHN) and the Multi-Branch Network (MBN). The MHN extends a standard backbone by appending lightweight output layers, or ”heads”, that jointly predict deepfake likelihood and compression level, enabling compression-aware detection with minimal architectural changes. The MBN combines multiple MHNs into a modular, parallel architecture, offering an alternative to conventional depth-based model scaling. Experiments on the FaceForensics++ and Celeb-DF datasets show that both MHN and MBN improve detection performance in compressed scenarios. Notably, MHN applied to a lightweight backbone outperforms deeper and more complex models without the multi-head extension, making the proposed solution well-suited for deployment in resource-constrained settings.

Detecting deepfake videos remains a challenging task, especially in scenarios involving unknown manipulation methods or unseen data distributions. Most existing video deepfake detection methods rely on high-level semantic features, which often lead to overfitting of facial identity information and poor transferability. In this work, we explore a novel perspective by modeling videos through 3D differential operations along temporal and spatial dimensions. To exploit the spatial–temporal variation information of the video content, the proposed approach decomposes videos into single-axis 1D differential signals, which are then transformed into 2D representations for efficient learning. This procedure enables the use of lightweight 2D CNNs while retaining directional forgery cues. Our experiments, aimed at analyzing whether these differential signals capture discriminative patterns useful for distinguishing real from fake content, show that the proposed method achieves strong intra-dataset performance and reveals complementary information across dimensions. These findings suggest that differential signals could potentially support generalization when integrated into broader detection frameworks. • We propose 3D Differential Decomposition modeling for deepfake video detection. • Multi-directional and multi-order differential operation are considered. • Optimization for differential order selection and fusion strategy are explored.

ICAO-compliant facial images, initially designed for secure biometric passports, are increasingly becoming central to identity verification in a wide range of application contexts, including border control, digital travel credentials, and financial services. While their standardization enables global interoperability, it also facilitates practices such as morphing and deepfakes, which can be exploited for harmful purposes like identity theft and illegal sharing of identity documents. Traditional countermeasures like Presentation Attack Detection (PAD) are limited to real-time capture and offer no post-capture protection. This survey paper investigates digital watermarking and steganography as complementary solutions that embed tamper-evident signals directly into the image, enabling persistent verification without compromising ICAO compliance. We provide the first comprehensive analysis of state-of-the-art techniques to evaluate the potential and drawbacks of the underlying approaches concerning the applications involving ICAO-compliant images and their suitability under standard constraints. We highlight key trade-offs, offering guidance for secure deployment in real-world identity systems.

The Fingerprint Liveness Detection Competition (LivDet) is a recurring benchmark series that evaluates the effectiveness of software-based Presentation Attack Detection (PAD) algorithms in fingerprint recognition. LivDet2025 presents three challenges: (1) "Liveness Detection in Action", requiring the integration of PAD with user-specific recognition; (2) "Fingerprint Representation", evaluating the compactness and discriminability of feature vectors; and (3) "Adversarial Robustness", assessing the resilience of PADs to adversarially-crafted presentation attack instruments. This edition marks a significant milestone with the inclusion of contactless fingerprint data, promoting interoperability and robustness across acquisition technologies. Furthermore, no training data was provided; participants must select and declare external datasets for model development. The competition was open to academic and industrial research groups, with all submitted algorithms evaluated on common datasets and under standardized protocols. LivDet2025 aims to provide a comprehensive assessment of PAD performance under realistic, multi-sensor, and multi-attack scenarios. Results reveal important trade-offs between PAD accuracy, usability, and computational efficiency. For instance, some systems achieved high presentation attack rejection at the cost of extremely high false rejection rates, while others optimised speed and generalizability but exhibited limited attack resilience.

Modern identity verification systems increasingly rely on facial images embedded in biometric documents such as electronic passports. To ensure global interoperability and security, these images must comply with strict standards defined by the International Civil Aviation Organization (ICAO), which specify acquisition, quality, and format requirements. However, once issued, these images may undergo unintentional degradations (e.g., compression, resizing) or malicious manipulations (e.g., morphing) and deceive facial recognition systems. In this study, we explore fragile watermarking, based on deep steganographic embedding as a proactive mechanism to certify the authenticity of ICAO-compliant facial images. By embedding a hidden image within the official photo at the time of issuance, we establish an integrity marker that becomes sensitive to any post-issuance modification. We assess how a range of image manipulations affects the recovered hidden image and show that degradation artifacts can serve as robust forensic cues. Furthermore, we propose a classification framework that analyzes the revealed content to detect and categorize the type of manipulation applied. Our experiments demonstrate high detection accuracy, including cross-method scenarios with multiple deep steganography-based models. These findings support the viability of fragile watermarking via steganographic embedding as a valuable tool for biometric document integrity verification.

Abstract Nowadays, fingerprint Presentation Attack Detection systems (PADs) are primarily based on deep learning architectures subjected to massive training. However, their performance decreases to never-seen-before attacks. With the goal of contributing to explaining this issue, we hypothesized that this limited ability to generalize is due to the lack of "representativeness" of the samples available for the PAD training. "Representativeness" is treated here from a geometrical perspective: the spread of samples into the feature space, especially near the decision boundaries. In particular, we explored the possibility of adopting three-dimensionality reduction methods to make the problem affordable through visual inspection. These methods enable visual inspection and interpretation by projecting data into two-dimensional spaces, facilitating the identification of weak areas in the decision regions estimated after the training phase. Our analysis delineates the benefits and drawbacks of each dimensionality reduction method and leads us to make substantial recommendations in the crucial phase of the training design.

Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) and established to investigate the use of synthetic data for training face recognition models. The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones. In the first task, the face recognition backbone was fixed and the dataset size was limited, while the second task provided almost complete freedom on the model backbone, the dataset, and the training pipeline. The submitted models were trained on existing and also new synthetic datasets and used clever methods to improve training with synthetic data. The submissions were evaluated and ranked on a diverse set of seven benchmarking datasets. The paper gives an overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets. Furthermore, the evaluation of submissions is extended to bias assessment across different demography groups. Lastly, an outlook on the current state of the research in training face recognition models using synthetic data is presented, and existing problems as well as potential future directions are also discussed.

The harmful utilization of DeepFake technology poses a significant threat to public welfare, precipitating a crisis in public opinion. Existing detection methodologies, predominantly relying on convolutional neural networks and deep learning paradigms, focus on achieving high in-domain recognition accuracy amidst many forgery techniques. However, overseeing the intricate interplay between textures and artifacts results in compromised performance across diverse forgery scenarios. This paper introduces a groundbreaking framework, denoted as Texture and Artifact Detector (TAD), to mitigate the challenge posed by the limited generalization ability stemming from the mutual neglect of textures and artifacts. Specifically, our approach delves into the similarities among disparate forged datasets, discerning synthetic content based on the consistency of textures and the presence of artifacts. Furthermore, we use a model ensemble learning strategy to judiciously aggregate texture disparities and artifact patterns inherent in various forgery types, thereby enabling the model’s generalization ability. Our comprehensive experimental analysis, encompassing extensive intra-dataset and cross-dataset validations along with evaluations on both video sequences and individual frames, confirms the effectiveness of TAD. The results from four benchmark datasets highlight the significant impact of the synergistic consideration of texture and artifact information, leading to a marked improvement in detection capabilities.

Modern Fingerprint Presentation Attack Detection (FPAD) modules have been particularly successful in avoiding attacks exploiting artificial fingerprint replicas against Automated Fingerprint Identification Systems (AFISs). As for several other domains, Machine and Deep Learning strongly contributed to this success, with all recent state-of-the-art detectors leveraging learning-based approaches. An insidious flip side is represented by adversarial attacks, namely, procedures intended to mislead a target detector. Indeed, despite this type of attack has been considered unrealistic, as it presupposes access to the communication channel between the sensor and the detector, in a recent work, we have highlighted the possibility of transferring a fingerprint adversarial attack from the digital domain to the physical one. In this work, we take a step further by introducing a new procedure designed to make the physical adversarial presentation attack i) more robust to the physical crafting of the PAI by exploiting explainability techniques, ii) easier to adapt to different fingerprint scanners and adversarial algorithms, and iii) usable in a black-box scenario. To quantify the impact of these novel adversarial presentation attacks family, designed to be robust to the physical crafting process, we assess the performance of both state-of-the-art PAD modules alone and integrated AFISs. Results highlight the approach’s feasibility, opening a new series of threats in the context of fingerprint PAD.

The International Fingerprint Liveness Detection Competition (LivDet) is a biennial event that invites academic and industry participants to prove their advancements in Fingerprint Presentation Attack Detection (PAD). This edition, LivDet2023, proposed two challenges, “Liveness Detection in Action” and “Fingerprint Representation”, to evaluate the efficacy of PAD embedded in verification systems and the effectiveness and compactness of feature sets. A third, “hidden” challenge is the inclusion of two subsets in the training set whose sensor information is unknown, testing participants’ ability to generalize their models. Only bona fide fingerprint samples were provided to participants, and the competition reports and assesses the performance of their algorithms suffering from this limitation in data availability.

When deepfakes are widespread on chatting platforms, they are expected to be subject to heavy resizing and compressing steps. In this paper, we present a tensor-based representation of compressed and resized images. Tensor embeds DCT features computed on multi-scaled and multi-compressed versions of the input facial image. Moreover, a custom deep-architecture is designed and trained on the proposed representation. Experimental results show its pros and cons with respect to state-of-the-art methods.

3D face reconstruction algorithms from images and videos are applied to many fields, from plastic surgery to the entertainment sector, thanks to their advantageous features. However, when looking at forensic applications, 3D face reconstruction must observe strict requirements that still make unclear its possible role in bringing evidence to a lawsuit. Shedding some light on this matter is the goal of the present survey, where we start by clarifying the relation between forensic applications and biometrics. To our knowledge, no previous work adopted this relation to make the point on the state of the art. Therefore, we analyzed the achievements of 3D face reconstruction algorithms from surveillance videos and mugshot images and discussed the current obstacles that separate 3D face reconstruction from an active role in forensic applications.

The International Fingerprint Liveness Detection Competition is an international biennial competition open to academia and industry with the aim to assess and report advances in Fingerprint Presentation Attack Detection. The proposed "Liveness Detection in Action" and "Fingerprint representation" challenges were aimed to evaluate the impact of a PAD embedded into a verification system, and the effectiveness and compactness of feature sets for mobile applications. Furthermore, we experimented a new spoof fabrication method that has particularly affected the final results. Twenty-three algorithms were submitted to the competition, the maximum number ever achieved by LivDet.

The diffusion of fingerprint verification systems for security applications makes it urgent to investigate the embedding of software-based presentation attack detection algorithms (PAD) into such systems. Companies and institutions need to know whether such integration would make the system more “secure” and whether the technology available is ready, and, if so, at what operational working conditions. Despite significant improvements, especially by adopting deep learning approaches to fingerprint PAD, current research did not state much about their effectiveness when embedded in fingerprint verification systems. We believe that the lack of works is explained by the lack of instruments to investigate the problem, that is, modeling the cause-effect relationships when two non-zero error-free systems work together. Accordingly, this paper explores the fusion of PAD into verification systems by proposing a novel investigation instrument: a performance simulator based on the probabilistic modeling of the relationships among the Receiver Operating Characteristics (ROC) of the two individual systems when PAD and verification stages are implemented sequentially. As a matter of fact, this is the most straightforward, flexible, and widespread approach. We carry out simulations on the PAD algorithms’ ROCs submitted to the most recent editions of LivDet (2017-2019), the state-of-the-art NIST Bozorth3, and the top-level Veryfinger 12 matchers. Reported experiments explore significant scenarios to get the conditions under which fingerprint matching with embedded PAD can improve, rather than degrade, the overall personal verification performance.

We investigated the threat level of realistic attacks using latent fingerprints against sensors equipped with state-of-art liveness detectors and fingerprint verification systems which integrate such liveness algorithms. To the best of our knowledge, only a previous investigation was done with spoofs from latent prints. In this paper, we focus on using snapshot pictures of latent fingerprints. These pictures provide molds, that allows, after some digital processing, to fabricate high-quality spoofs. Taking a snapshot picture is much simpler than developing fingerprints left on a surface by magnetic powders and lifting the trace by a tape. What we are interested here is to evaluate preliminary at which extent attacks of the kind can be considered a real threat for state-of-art fingerprint liveness detectors and verification systems. To this aim, we collected a novel data set of live and spoof images fabricated with snapshot pictures of latent fingerprints. This data set provide a set of attacks at the most favourable conditions. We refer to this method and the related data set as “ScreenSpoof”. Then, we tested with it the performances of the best liveness detection algorithms, namely, the three winners of the LivDet competition. Reported results point out that the ScreenSpoof method is a threat of the same level, in terms of detection and verification errors, than that of attacks using spoofs fabricated with the full consensus of the victim. We think that this is a notable result, never reported in previous work.

We present a novel descriptor for crowd behavior analysis and anomaly detection. The goal is to measure by appropriate patterns the speed of formation and disintegration of groups in the crowd. This descriptor is inspired by the concept of one-dimensional local binary patterns: in our case, such patterns depend on the number of group observed in a time window. An appropriate measurement unit, named “trit” (trinary digit), represents three possible dynamic states of groups on a certain frame. Our hypothesis is that abrupt variations of the groups' number may be due to an anomalous event that can be accordingly detected, by translating these variations on temporal trit-based sequence of strings which are significantly different from the one describing the “no-anomaly” one. Due to the peculiarity of the rationale behind this work, relying on the number of groups, three different methods of people group's extraction are compared. Experiments are carried out on the Motion-Emotion benchmark data set. Reported results point out in which cases the trit-based measurement of group dynamics allows us to detect the anomaly. Besides the promising performance of our approach, we show how it is correlated with the anomaly typology and the camera's perspective to the crowd's flow (frontal, lateral).

In this study we investigate a textural processing method of electroencephalography (EEG) signal as an indicator to estimate the driver's vigilance in a hypothetical Brain-Computer Interface (BCI) system. The novelty of the solution proposed relies on employing the one-dimensional Local Binary Pattern (1D-LBP) algorithm for feature extraction from pre-processed EEG data. From the resulting feature vector, the classification is done according to three vigilance classes: awake, tired and drowsy. The claim is that the class transitions can be detected by describing the variations of the micro-patterns' occurrences along the EEG signal. The 1D-LBP is able to describe them by detecting mutual variations of the signal temporarily “close” as a short bit-code. Our analysis allows to conclude that the 1D-LBP adoption has led to significant performance improvement. Moreover, capturing the class transitions from the EEG signal is effective, although the overall performance is not yet good enough to develop a BCI for assessing the driver's vigilance in real environments.

In the last five years, deep learning methods, in particular CNN, have attracted considerable attention in the field of face-based recognition, achieving impressive results. Despite this progress, it is not yet clear precisely to what extent deep features are able to follow all the intra-class variations that the face can present over time. In this paper we investigate the performance the performance improvement of face recognition systems by adopting self updating strategies of the face templates. For that purpose, we evaluate the performance of a well-known deep-learning face representation, namely, FaceNet, on a dataset that we generated explicitly conceived to embed intra-class variations of users on a large time span of captures: the APhotoEveryday (APE) dataset11https://github.com/PRALabBiometrics/APhotoEverydayDB. Moreover, we compare these deep features with handcrafted features extracted using the BSIF algorithm. In both cases, we evaluate various template update strategies, in order to detect the most useful for such kind of features. Experimental results show the effectiveness of “optimized” self-update methods with respect to systems without update or random selection of templates.

The similarities among different acquisitions of the same fingerprint have never been taken into account, so far, in the feature space designed to detect fingerprint presentation attacks. Actually, the existence of such resemblances has only been shown in a recent work where the authors have been able to describe what they called the “user-specific effect”. We present in this paper a first attempt to take advantage of this in order to improve the performance of a FPAD system. In particular, we conceived a binary code of three bits aimed to “detect” such effect. Coupled with a classifier trained according to the standard protocol followed, for example, in the LivDet competition, this approach allowed us to get a better accuracy compared to that obtained with the “generic users” classifier alone.

Prior work has shown that multibiometric systems are vulnerable to presentation attacks, assuming that their matching score distribution is identical to that of genuine users, without fabricating any fake trait. We have recently shown that this assumption is not representative of current fingerprint and face presentation attacks, leading one to overestimate the vulnerability of multibiometric systems, and to design less effective fusion rules. In this paper, we overcome these limitations by proposing a statistical meta-model of face and fingerprint presentation attacks that characterizes a wider family of fake score distributions, including distributions of known and, potentially, unknown attacks. This allows us to perform a thorough security evaluation of multibiometric systems against presentation attacks, quantifying how their vulnerability may vary also under attacks that are different from those considered during design, through an uncertainty analysis. We empirically show that our approach can reliably predict the performance of multibiometric systems even under never-before-seen face and fingerprint presentation attacks, and that the secure fusion rules designed using our approach can exhibit an improved trade-off between the performance in the absence and in the presence of attack. We finally argue that our method can be extended to other biometrics besides faces and fingerprints.

Systems for still-to-video face recognition (FR) seek to detect the presence of target individuals based on reference facial still images or mug-shots. These systems encounter several challenges in video surveillance applications due to variations in capture conditions (e.g., pose, scale, illumination, blur and expression) and to camera inter-operability. Beyond these issues, few reference stills are available during enrollment to design representative facial models of target individuals. Systems for still-to-video FR must therefore rely on adaptation, multiple face representation, or synthetic generation of reference stills to enhance the intra-class variability of face models . Moreover, many FR systems only match high quality faces captured in video, which further reduces the probability of detecting target individuals. Instead of matching faces captured through segmentation to reference stills, this paper exploits Adaptive Appearance Model Tracking (AAMT) to gradually learn a track-face-model for each individual appearing in the scene. The Sequential Karhunen–Loeve technique is used for online learning of these track-face-models within a particle filter-based face tracker. Meanwhile, these models are matched over successive frames against the reference still images of each target individual enrolled to the system, and then matching scores are accumulated over several frames for robust spatiotemporal recognition. A target individual is recognized if scores accumulated for a track-face-model over a fixed time surpass some decision threshold. The main advantage of AAMT over traditional still-to-video FR systems is the greater diversity of facial representation that may be captured during operations, and this can lead to better discrimination for spatiotemporal recognition. Compared to state-of-the-art adaptive biometric systems, the proposed method selects facial captures to update an individual׳s face model more reliably because it relies on information from tracking. Simulation results obtained with the Chokepoint video dataset indicate that the proposed method provides a significantly higher level of performance compared state-of-the-art systems when a single reference still per individual is available for matching. This higher level of performance is achieved when the diverse facial appearances that are captured in video through AAMT correspond to that of reference stills.

Gait recognition is an emerging biometric technology that identifies people through the analysis of the way they walk. The challenge of model-free based gait recognition is to cope with various intra-class variations such as clothing variations, carrying conditions and angle variations that adversely affect the recognition performance. This paper proposes a method to select the most discriminative human body part based on group Lasso of motion to reduce the intra-class variation so as to improve the recognition performance. The proposed method is evaluated using CASIA Gait Dataset B. Experimental results demonstrate that the proposed technique gives promising results.

Recently, there has been a growing interest in the use of brain activity for biometric systems. However, so far these studies have focused mainly on basic features of the Electroencephalography. In this study we propose an approach based on phase synchronization, to investigate personal distinctive brain network organization. To this end, the importance, in terms of centrality, of different regions was determined on the basis of EEG recordings. We hypothesized that nodal centrality enables the accurate identification of individuals. EEG signals from a cohort of 109 64-channels EEGs were band-pass filtered in the classical frequency bands and functional connectivity between the sensors was estimated using the Phase Lag Index. The resulting connectivity matrix was used to construct a weighted network, from which the nodal Eigenvector Centrality was computed. Nodal centrality was successively used as feature vector. Highest recognition rates were observed in the gamma band (equal error rate ( EER) = 0.044) and high beta band ( EER = 0.102). Slightly lower recognition rate was observed in the low beta band ( EER = 0.144), while poor recognition rates were observed for the others frequency bands. The reported results show that resting-state functional brain network topology provides better classification performance than using only a measure of functional connectivity, and may represent an optimal solution for the design of next generation EEG based biometric systems. This study also suggests that results from biometric systems based on high-frequency scalp EEG features should be interpreted with caution.

Recent works have shown that multi-modal biometric systems are not robust against spoofing attacks [12, 15,13]. However, this conclusion has been obtained under the hypothesis of a "worst case" attack, where the attacker is able to replicate perfectly the genuine biometric traits. Aim of this paper is to analyse the robustness of some multi-modal verification systems, combining fingerprint and face bio-metrics, under realistic spoofing attacks, in order to investigate the validity of the results obtained under the worst-case attack assumption.

Spoofing is an open-issue for fingerprint recognition systems. It consists in submitting an artificial fingerprint replica from a genuine user. Current sensors provide an image which is then processed as a “true” fingerprint. Recently, the so-called 3rd-level features, namely, pores, which are visible in high-definition fingerprint images, have been used for matching. In this paper, we propose to analyse pores location for characterizing the “liveness” of fingerprints. Experimental results on a large dataset of spoofed and live fingerprints show the benefits of the proposed approach.