This paper explores the application of large language models (LLMs), like ChatGPT, for biometric tasks. We specifically examine the capabilities of ChatGPT in performing biometric-related tasks, with an emphasis on face recognition, gender detection, and age estimation. Since biometrics are considered as sensitive information, ChatGPT avoids answering direct prompts, and thus we crafted a prompting strategy to bypass its safeguard and evaluate the capabilities for biometrics tasks. Our study reveals that ChatGPT recognizes facial identities and differentiates between two facial images with considerable accuracy. Additionally, experimental results demonstrate remarkable performance in gender detection and reasonable accuracy for the age estimation tasks. Our findings shed light on the promising potentials in the application of LLMs and foundation models for biometrics.
The task of deepfakes detection is far from being solved by speech or vision researchers. Several publicly available databases of fake synthetic video and speech were built to aid the development of detection methods. However, existing databases typically focus on visual or voice modalities and provide no proof that their deepfakes can in fact impersonate any real person. In this paper, we present the first realistic audio-visual database of deepfakes SWAN-DF, where lips and speech are well synchronized and video have high visual and audio qualities. We took the publicly available SWAN dataset of real videos with different identities to create audio-visual deepfakes using several models from DeepFaceLab and blending techniques for face swapping and HiFiVC, DiffVC, YourTTS, and FreeVC models for voice conversion. From the publicly available speech dataset LibriTTS, we also created a separate database of only audio deepfakes LibriTTS-DF using several latest text to speech methods: YourTTS, Adaspeech, and TorToiSe. We demonstrate the vulnerability of a state of the art speaker recognition system, such as ECAPA-TDNN-based model from SpeechBrain, to the synthetic voices. Similarly, we tested face recognition system based on the MobileFaceNet architecture to several variants of our visual deepfakes. The vulnerability assessment show that by tuning the existing pretrained deepfake models to specific identities, one can successfully spoof the face and speaker recognition systems in more than 90% of the time and achieve a very realistic looking and sounding fake video of a given person.
Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin. The main reason are the biases inside datasets, unbalanced demographics, used to train theses models. Unfortunately, collecting a large-scale balanced dataset with respect to various demographics is impracticable. In this paper, we investigate as an alternative the generation of a balanced and possibly bias-free synthetic dataset that could be used to train, to regularize or to evaluate deep learning-based facial recognition models. We propose to use a simple method for modeling and sampling a disentangled projection of a StyleGAN latent space to generate any combination of demographic groups (e.g. $hispanic-female$). Our experiments show that we can synthesis any combination of demographic groups effectively and the identities are different from the original training dataset. We also released the source code.
Heterogeneous Face Recognition (HFR) aims to match face images across different domains, such as thermal and visible spectra, expanding the applicability of Face Recognition (FR) systems to challenging scenarios. However, the domain gap and limited availability of large-scale datasets in the target domain make training robust and invariant HFR models from scratch difficult. In this work, we treat different modalities as distinct styles and propose a framework to adapt feature maps, bridging the domain gap. We introduce a novel Conditional Adaptive Instance Modulation (CAIM) module that can be integrated into pre-trained FR networks, transforming them into HFR networks. The CAIM block modulates intermediate feature maps, to adapt the style of the target modality effectively bridging the domain gap. Our proposed method allows for end-to-end training with a minimal number of paired samples. We extensively evaluate our approach on multiple challenging benchmarks, demonstrating superior performance compared to state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available.
In this paper, we present EdgeFace, a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.
The accuracy of finger vein recognition systems gets degraded due to low and uneven contrast between veins and surroundings, often resulting in poor detection of vein patterns. We propose a finger-vein enhancement technique, ResFPN (Residual Feature Pyramid Network), as a generic preprocessing method agnostic to the recognition pipeline. A bottom-up pyramidal architecture using the novel Structure Detection block (SDBlock) facilitates extraction of veins of varied widths. Using a feature aggregation module (FAM), we combine these vein-structures, and train the proposed ResFPN for detection of veins across scales. With enhanced presentations, our experiments indicate a reduction upto 5% in the average recognition errors for commonly used recognition pipeline over two publicly available datasets. These improvements are persistent even in cross-dataset scenario where the dataset used to train the ResFPN is different from the one used for recognition.
The demographic disparity of biometric systems has led to serious concerns regarding their societal impact as well as applicability of such systems in private and public domains. A quantitative evaluation of demographic fairness is an important step towards understanding, assessment, and mitigation of demographic bias in biometric applications. While few, existing fairness measures are based on post-decision data (such as verification accuracy) of biometric systems, we discuss how pre-decision data (score distributions) provide useful insights towards demographic fairness. In this paper, we introduce multiple measures, based on the statistical characteristics of score distributions, for the evaluation of demographic fairness of a generic biometric verification system. We also propose different variants for each fairness measure depending on how the contribution from constituent demographic groups needs to be combined towards the final measure. In each case, the behavior of the measure has been illustrated numerically and graphically on synthetic data. The demographic imbalance in benchmarking datasets is often overlooked during fairness assessment. We provide a novel weighing strategy to reduce the effect of such imbalance through a non-linear function of sample sizes of demographic groups. The proposed measures are independent of the biometric modality, and thus, applicable across commonly used biometric modalities (e.g., face, fingerprint, etc.).
Heterogeneous Face Recognition (HFR) refers to matching face images captured in different domains, such as thermal to visible images (VIS), sketches to visible images, near-infrared to visible, and so on. This is particularly useful in matching visible spectrum images to images captured from other modalities. Though highly useful, HFR is challenging because of the domain gap between the source and target domain. Often, large-scale paired heterogeneous face image datasets are absent, preventing training models specifically for the heterogeneous task. In this work, we propose a surprisingly simple, yet, very effective method for matching face images across different sensing modalities. The core idea of the proposed approach is to add a novel neural network block called Prepended Domain Transformer (PDT) in front of a pre-trained face recognition (FR) model to address the domain gap. Retraining this new block with few paired samples in a contrastive learning setup was enough to achieve state-of-the-art performance in many HFR benchmarks. The PDT blocks can be retrained for several source-target combinations using the proposed general framework. The proposed approach is architecture agnostic, meaning they can be added to any pre-trained FR models. Further, the approach is modular and the new block can be trained with a minimal set of paired samples, making it much easier for practical deployment. The source code and protocols will be made available publicly.
The vulnerability against presentation attacks is a crucial problem undermining the wide-deployment of face recognition systems. Though presentation attack detection (PAD) systems try to address this problem, the lack of generalization and robustness continues to be a major concern. Several works have shown that using multi-channel PAD systems could alleviate this vulnerability and result in more robust systems. However, there is a wide selection of channels available for a PAD system such as RGB, Near Infrared, Shortwave Infrared, Depth, and Thermal sensors. Having a lot of sensors increases the cost of the system, and therefore an understanding of the performance of different sensors against a wide variety of attacks is necessary while selecting the modalities. In this work, we perform a comprehensive study to understand the effectiveness of various imaging modalities for PAD. The studies are performed on a multi-channel PAD dataset, collected with 14 different sensing modalities considering a wide range of 2D, 3D, and partial attacks. We used the multi-channel convolutional network-based architecture, which uses pixel-wise binary supervision. The model has been evaluated with different combinations of channels, and different image qualities on a variety of challenging known and unknown attack protocols. The results reveal interesting trends and can act as pointers for sensor selection for safety-critical presentation attack detection systems. The source codes and protocols to reproduce the results are made available publicly making it possible to extend this work to other architectures.
Automatic methods for detecting presentation attacks are essential to ensure the reliable use of facial recognition technology. Most of the methods available in the literature for presentation attack detection (PAD) fails in generalizing to unseen attacks. In recent years, multi-channel methods have been proposed to improve the robustness of PAD systems. Often, only a limited amount of data is available for additional channels, which limits the effectiveness of these methods. In this work, we present a new framework for PAD that uses RGB and depth channels together with a novel loss function. The new architecture uses complementary information from the two modalities while reducing the impact of overfitting. Essentially, a cross-modal focal loss function is proposed to modulate the loss contribution of each channel as a function of the confidence of individual channels. Extensive evaluations in two publicly available datasets demonstrate the effectiveness of the proposed approach.