Face Authentication System Research Articles

A Multi-task Adversarial Attack Against Face Authentication

Deep-learning-based identity management systems, such as face authentication systems, are vulnerable to adversarial attacks. However, existing attacks are typically designed for single-task purposes, which means they are tailored to exploit vulnerabilities unique to the individual target rather than being adaptable for multiple users or systems. This limitation makes them unsuitable for certain attack scenarios, such as morphing, universal, transferable, and counter attacks. In this paper, we propose a multi-task adversarial attack algorithm called MTADV that are adaptable for multiple users or systems. By interpreting these scenarios as multi-task attacks, MTADV is applicable to both single- and multi-task attacks, and feasible in the white- and gray-box settings. Furthermore, MTADV is effective against various face datasets, including LFW, CelebA, and CelebA-HQ, and can work with different deep learning models, such as FaceNet, InsightFace, and CurricularFace. Importantly, MTADV retains its feasibility as a single-task attack targeting a single user/system. To the best of our knowledge, MTADV is the first adversarial attack method that can target all of the aforementioned scenarios in one algorithm.

Text-Guided Synthesis of Masked Face Images

The COVID-19 pandemic has made us all understand that wearing a face mask protects us from the spread of respiratory viruses. The face authentication systems, which are trained on the basis of facial key points such as the eyes, nose, and mouth, found it difficult to identify the person when the majority of the face is covered by the face mask. Removing the mask for authentication will cause the infection to spread. The possible solutions are: (a) to train the face recognition systems to identify the person with the upper face features (b) Reconstruct the complete face of the person with a generative model. (c) train the model with a dataset of the masked faces of the people. In this paper, we explore the scope of generative models for image synthesis. We used stable diffusion to generate masked face images of popular celebrities on various text prompts. A realistic dataset of 15K masked face images of 100 celebrities is generated and is called the Realistic Synthetic Masked Face Dataset (RSMFD). The model and the generated dataset will be made public so that researchers can augment the dataset. According to our knowledge, this is the largest masked face recognition dataset with realistic images. The generated images were tested on popular deep face recognition models and achieved significant results. The dataset is also trained and tested on some of the famous image classification models, and the results are competitive. The dataset is available on this link:- https://drive.google.com/drive/folders/1yetcgUOL1TOP4rod1geGsOkIrIJHtcEw?usp=sharing

Spoofing Attacks and Anti-Spoofing Methods for Face Authentication Over Smartphones

The ubiquitous usages of smartphones demand reliable mobile authentication systems, which are expected to play an indispensable role in protecting users' sensitive and private information. Among various mobile authentication mechanisms, face authentication (FA) has become the most popular choice on modern smartphones, owing to its excellent performance and user experience. Unfortunately, emerging advanced attacks have brought in severe security concerns against FA systems (e.g., privacy leakage, property damage), which have also triggered increased attention on face anti-spoofing designs. This paper provides a concise review of the advanced face anti-spoofing systems over smartphones from a practical perspective. We first review the presentation attacks (PAs) toward FA systems and classify them according to the geometry and dynamic property of the presentation mediums. Then we survey the state-ofthe- art presentation attack detection (PAD) approaches over smartphones and categorize these methods into four categories based on the cues they leverage. Furthermore, we present a comprehensive comparison of their advantages and disadvantages from various practical aspects. Finally, we provide recommendations for future directions. We hope our viewpoints would shed light on potential pathways for more reliable FA in the future.

Digital competences in research: creativity and entrepreneurship as essential predictors for teacher training

AbstractThe first purpose of this study was to analyse the digital research competences of higher education teaching staff, depending on whether the level of creativity of the teacher to initiate new research projects and their level of entrepreneurial spirit was low/good. Following, it was analysed whether the use of different emerging technologies significantly affect the digital skills of teachers in research work; and to know in what order the use of these emerging technologies or the combination of several of them affect the digital competences of teachers. A ex post facto design was used with a sample of 1740 Higher Education teachers. Digital skills were measured using the instrument of Guillén-Gámez et al. (Educ Inf Technol 10.1007/s10639-023-11895-2, 2023). The levels of creativity and entrepreneurship were analyzed with dichotomous variables from a 10-point Likert scale (less than 7 points-low level, greater than or equal to 7-good level). The results showed that, although teachers possessed an adequate level of digital research skills, this could vary depending on transversal skills such as creativity and entrepreneurship, with large differences when these skills were at a basic level. Furthermore, depending on whether teachers had research experience in XR technology, cryptocurrencies, facial authentication systems, wearables or robotics, amongst others, this significantly affected the level of digital competence in research. The added value of this study lies on the one hand, in the fact that there are hardly any studies that analyse this subject; and on the other hand, the implications that this could have for institutions to launch training initiatives for their teaching staff in emerging technologies, as well as in transversal competences in any disciplinary field.

Biometric face authentication system for secure smart office environments

<span>The use of the smart office concept in security has increased significantly recently. One of the areas of concern is the use of facial finger biometric technology for authentication systems, for example, authentication to enter a particular room in an office. This paper aims to describe a new prototype for office door automation and security that combines facial biometric technology and NodeMCU. Hopefully, this system will help increase the safety and comfort of office employees with easy installation and low cost. This system automatically controls (opens or closes) the door based on the biometrics of the user’s face registered in the database on the NodeMCU microcontroller. The main system comprises a NodeMCU microcontroller, face sensors, and a door lock system.</span>

SonarGuard: Ultrasonic Face Liveness Detection on Mobile Devices

Liveness detection has been widely applied in face authentication systems to combat malicious attacks. However, existing methods purely depending on visual frames become vulnerable once visual perception is not reliable. The emerging face spoof and forge techniques urge the systems to exploit the defensive potential of non-visual modalities. To tackle this challenge, we introduce SonarGuard, a system combining ultrasonic and visual information to achieve robust liveness detection on mobile devices. More specifically, SonarGuard simultaneously extracts micro-doppler signatures from ultrasound reflections and motion trajectories from video frames both corresponding to the user’s lip movement. To further confirm the collected ultrasonic and visual information is not derived from malicious audio/video attacks, we consolidate the system via introducing a cross-modal matching mechanism, which demands the inherent consistency between these two modalities. Extensive experiments on a new dataset collected with existing mobile devices demonstrate that the proposed system could achieve average classification error rate of 0.91% under presentation attacks. This result indicates that SonarGuard can boost the security of face authenfication systems in real world usage without additional hardware modification.

Face presentation attack detection performances of facial regions with multi-block LBP features.

Biometric recognition systems are frequently used in daily life although they are vulnerable to attacks. Today, especially the increasing use of face authentication systems has made these systems the target of face presentation attacks (FPA). This has increased the need for sensitive systems detecting the FPAs. Recently surgical masks, frequently used due to the pandemic, directly affect the performance of face recognition systems. Researchers design face recognition systems only from the eye region. This motivated us to evaluate the FPA detection performance of the eye region. Based on this, in cases where the whole face is not visible, the FPA detection performance of other parts of the face has also been examined. Therefore, in this study, FPA detection performances of facial regions of wide face, cropped face, eyes, nose, and mouth was investigated. For this purpose, the facial regions were determined and normalized, and texture features were extracted using powerful texture descriptor local binary patterns (LBP) due to its easy computability and low processing complexity. Multi-block LBP features are used to obtain more detailed texture information. Generally uniform LBP patterns are used for feature extraction in the literature. In this study, the FPA detection performances of both uniform LBP patterns and all LBP patterns were investigated. The size of feature vector is reduced by principal component analysis, and real/fake classification is performed with support vector machines. Experimental results on NUAA, CASIA, REPLAY-ATTACK and OULU-NPU datasets show that the use of all patterns increased the performance of FPA detection.

Local Binary Pattern Histogram Based Web Facial Authentication System

The objective of the project is to Detect and Recognize Human Facial Features via a Camera. The basic concept of this project is:- To convert the input image to HSV format to extract the binary image and additionally remove the noise from binary image using morphological operations and finally then contours are used to segment out the region of interest and further the region is analyzed to get the final result. While biometric data is generally considered one of the most reliable authentication methods, it also carries significant risk. That’s because if someone’s credit card details are hacked, that person has the option to freeze their credit and take steps to change the personal information that was breached. What do you do if you lose your digital ‘face’? Around the world, biometric information is being captured, stored, and analyzed in increasing quantities, often by organizations and governments, with a mixed record on cybersecurity. A question increasingly being asked is, how safe is the infrastructure that holds and processes all this data? As facial recognition software is still in its relative infancy, the laws governing this area are evolving (and sometimes non-existent).

Poisoning attacks on face authentication systems by using the generative deformation model

Poisoning attacks on face authentication systems by using the generative deformation model

Overcoming deep learning subclass imbalances: Comparing the transfer of identity across a racial transformation

As facial authentication systems become an increasingly advantageous technology, the subtle inaccuracy under certain subgroups grows in importance. As researchers perform data augmentation to increase subgroup accuracies, it is critical that the data augmentation approaches are understood. We specifically research the impact that the data augmentation method of racial transformation has upon the identity of the individual according to a facial authentication network. This demonstrates whether the racial transformation maintains critical aspects to an individual identity or whether the data augmentation method creates the equivalence of an entirely new individual for networks to train upon. We demonstrate our method for racial transformation based on other top research articles methods, display the embedding distance distribution of augmented faces compared with the embedding distance of non-augmented faces and explain to what extent racial transformation maintains critical aspects to an individual’s identity.

Post-Quantum Biometric Authentication Based on Homomorphic Encryption and Classic McEliece

Homomorphic encryption is a powerful mechanism that allows sensitive data, such as biometric data, to be compared in a protected way, revealing only the comparison result when the private key is known. This is very useful for non-device-centric authentication architectures with clients that provide protected data and external servers that authenticate them. While many reported solutions do not follow standards and are not resistant to quantum computer attacks, this work proposes a secure biometric authentication scheme that applies homomorphic encryption based on the Classic McEliece public-key encryption algorithm, which is a round 4 candidate of the NIST post-quantum standardization process. The scheme applies specific steps to transform the features extracted from biometric samples. Its use is proposed in a non-device-centric biometric authentication architecture that ensures user privacy. Irreversibility, revocability and unlinkability are satisfied and the scheme is robust to stolen-device, False-Acceptance Rate (FAR) and similarity-based attacks as well as to honest-but-curious servers. In addition to the security achieved by the McEliece system, which remains stable over 40 years of attacks, the proposal allows for very reduced storage and communication overheads as well as low computational cost. A practical implementation of a non-device-centric facial authentication system is illustrated based on the generation and comparison of protected FaceNet embeddings. Experimental results with public databases show that the proposed scheme improves the accuracy and the False-Acceptance Rate of the unprotected scheme, maintaining the False-Rejection Rate, allows real-time execution in clients and servers for Classic McEliece security parameter sets of 128 and 256 bits (mceliece348864 and mceliece6688128, respectively), and reduces storage requirements in more than 90.5% compared to the most reduced-size homomorphic encryption-based schemes with post-quantum security reported in the literature.

Where Are the Dots: Hardening Face Authentication on Smartphones With Unforgeable Eye Movement Patterns

With the ubiquitous adoption, mobile face authentication systems have been facing constant security challenges, particularly the spoofing risks. Except for those using specialized hardware, existing proposals for face anti-spoofing on mainstream smartphones either leverage people’s 3D face characteristics or various facial expressions. While showing progress towards more resilient face authentication, they are still vulnerable to recent advanced attacks (e.g., 3D mask attacks, video attacks, etc.). This paper presents GazeGuard, an on-device face anti-spoofing system that leverages unpredictable and unforgeable eye movement patterns to provide strong security guarantees against all known attacks. Targeting mainstream smartphones, GazeGuard is designed to conduct eye movement-based authentication using only 2D front cameras. Specifically, by presenting a series of short-lasting random dots on the screen (named gazecode), GazeGuard simultaneously captures a user’s gaze responses and the corresponding deformed periocular features to ensure both the freshness and correctness for the anti-spoofing face authentication. We have extensively tested GazeGuard’s performance over 50 volunteers. Using a 4-digit gazecode (just four random dots), GazeGuard achieves an average 90.39% authentication accuracy and 81.57 out of 100 System Usability Scale (SUS) scores. Under the same settings, GazeGuard achieves detection accuracy of 95.72% for image attack, 95.59% for video attack, 99.73% for 3D mask attack, and 100% for physical adversarial attack.

Research and development of a two-factors face authentication system using an invisible F-QR code on ID card by 1064 nm laser and AI camera

The face authentication system using two security factors: an invisible F-QR (face QR) code printed on an ID card and face recognition using AI camera is presented in this paper. F-QR codes with facial features are generated by a chain processing of face detection, face property extraction and QR code generation. The F-QR code is printed on a plastic ID card using a 1064 nm fiber laser. The ID card is made of special materials, including a layer of filter material that allows the 1064 nm laser to pass through while blocking visible lights so that the printed F-QR code on the card is invisible to the human eye or conventional QR code readers. Face authentication is implemented using a dedicated invisible F-QR code reader combined with an AI camera to decide the Cosine similarity between two face feature vectors to make an accurate decision for the authentication.

Detection of presentation attacks on facial authentication systems using special devices

The article proposes a feature system designed to detect presentation attacks on facial authentication systems. In this type of attack, an attacker disguises as an authorized user using his image. The feature system assumes the possibility of using one or more special imaging sensors in addition to the basic RGB camera (thermal cameras, depth cameras, infrared cameras). The method has demonstrated a low error rate on the WMCA dataset, while experiments have shown its ability to remain effective in the case of the lack of training data. The comparative experiments carried out showed that the proposed method surpassed the RDWT-Haralick-SVM algorithm, and also approached the results of the MC-CNN algorithm, based on deep learning, which requires a significantly larger amount of training data.

Cloud Data Access Prevention Method in Face Recognition Technology Based on Computer Vision

With the development of cloud technology and the innovation of information network technology, people’s dependence on the network has gradually increased, and there are some loopholes in cloud data access. The traditional account permission model can no longer meet the conditions of cloud data access alone. If the visitor temporarily leaves the computer or goes out in an emergency, the data are likely to be leaked. Based on the importance and concern of this issue, some scholars have proposed an authentication system combined with biometric face recognition, but the traditional face recognition system has certain security risks. Such as using face pictures and videos to deceive the system, tampering with face templates, etc. Based on this, this paper proposes an encrypted face authentication system based on CNN neural network. Through the authentication of face data, the content transmission of each part is carried out in the form of ciphertext to ensure the security of information. The experimental results in this paper show that the authentication accuracy rate of DeepID is 94% when it is not encrypted, and the authentication accuracy rate decreases slightly after encryption, which is 93.3%. It is similar in other cases. When the network structure and data set remain unchanged, encryption reduces the authentication accuracy rate by 0.3%–2.4%. It can be seen that the scheme proposed in this chapter improves the system security at the cost of a smaller accuracy rate.

Deteksi Non-Spoofing Wajah pada Video secara Real Time Menggunakan Faster R-CNN

Face non-spoofing detection is an important job used to ensure authentication security by performing an analysis of the captured faces. Face spoofing is the process of fake faces by other people to gain illegal access to the biometric system which can be done by displaying videos or images of someone's face on the monitor screen or using printed images. There are various forms of attacks that can be carried out on the face authentication system in the form of face sketches, face photos, face videos and 3D face masks. Such attacks can occur because photos and videos of faces from users of the facial authentication system are very easy to obtain via the internet or cameras. To solve this problem, in this research proposes a non-spoofing face detection model on video using Faster R-CNN. The results obtained in this study are the Faster R-CNN model that can detect non-spoof and spoof face in real time using the Raspberry Pi as a camera with a frame rate of 1 fps.

DOG-ADTCP: A new feature descriptor for protection of face identification system

Nowadays the face biometric system is gaining popularity for authentication in access control applications. At the same time, the threats to authentication systems are also increased in terms of spoofing or presentation attacks where an intruder attempts to spoof the face recognition system by using genuine user photos or video to gain access. In order to effectively secure the secrecy of a genuine user, there is an urgent need for building a face authentication system with anti-spoofing countermeasures. In this paper, we introduce a novel face anti-spoofing approach, which is mainly based on contrast and texture features of both real and spoof photos. A modified Difference of Gaussian (DOG) filtering method and Angle Directional Ternary Co-relation pattern (ADTCP) are used. The publicly available NUAA, MSU-MFSD and REPLAY-ATTACK photo-impostor datasets are tested on the approach, which includes images with different illumination and area of the face. The accuracy of the proposed approach is evaluated using different metrics. The results show that our proposed method is superior to other state-of-the-art (SOTA) practices when tested on three photo-impostor datasets.

Dynamic face authentication systems: Deep learning verification for camera close-Up and head rotation paradigms

The popularity of face-authentication systems has also generated interest in the study of malicious authentication attempts, such as face spoofing attacks. In this study we investigate two dynamic face-authentication challenges: the camera close-up, and head-rotation paradigms. For each paradigm we developed an ML-based face-authentication system that performs the tasks of liveness detection and face verification. In order to generate structured data-representations from the videos collected in the wild, we designed feature representations that extract three-dimensional and spatial characteristics of a face, while also capturing the particular liveness cues of the requested challenge-based movements. Furthermore, a set of Neural-Network models that employ Convolutional Neural Networks and Siamese Neural Network architectures were proposed. To train and test our models we collected a dataset of 177 live videos recorded by 41 different subjects and a set of 243 attack attempts in uncontrolled scenarios. The resulting NN models yield good performance against multiple types of media-based attacks (printed-attacks, screen-attacks, 2D-masks, videos acquired from public social media, deep fakes). The camera close-up system presented an overall liveness detection accuracy of 97.7% and a face verification accuracy of 97.6%. On the other hand, the evaluation of the head-rotation system resulted in a liveness detection accuracy of 92.4% and face verification accuracy of 98.1%. Face authentication methods based on dynamic user-challenges constitute a scalable approach that does not require specialized hardware to increase the security of face authentication systems in realistic usage scenarios. The proposed methods not only make it harder for attackers to generate spoofing attacks, but they also constitute a practical complement to static biometric authentication systems.

IFace 1.1: A Proof-of-Concept of a Facial Authentication Based Digital ID for Smart Cities

“Smart Cities” are a viable option to various issues caused by accelerated urban growth. To make smart cities a reality, smart citizens need to be connected to the “Smart City” through a digital ID. A digital ID allows citizens to make easy and effective use of amenities provided by the smart city such as healthcare, transport, finance, and energy. In this paper, we propose a proof-of-concept of facial authentication based end-to-end digital ID system for a smart city. Facial authentication systems are prone to various biometric template attacks and cyber security attacks. Our proposed system is designed to detect the first type of attack especially deepfake and presentation attacks. Users are authenticated each time before using facilities in the smart city. Authentication is performed on edge devices, making the process more secure as no data leaves the device during authentication. Facial data is stored at the cloud in a look up table format with an unidentifiable username. Our proposed solution achieved 97% accuracy in authentication with a False Rejection Ratio of 2% and False Acceptance Ratio of 3%.

Efficient-SwishNet Based System for Facial Emotion Recognition

Facial emotion recognition (FER) is an important research area in artificial intelligence and has many applications i.e., face authentication systems, e-learning, entertainment, deepfakes detection, etc. FER is still a challenging task due to more intra-class variations of emotions. Although existing deep learning methods have achieved good performance for FER. However, still there exists a need to develop efficient and effective FER systems robust to certain conditions i.e., variations in illumination, face angles, gender, race, background settings and people belonging to diverse geographical regions. Moreover, a generalized model for classification of human emotions is required to be implemented in computer systems so that they can interact with humans according to their emotions and improve their interaction. This work presents a novel light-weight Efficient-SwishNet model for emotion recognition that is robust towards the aforementioned conditions. We have introduced a low-cost, smooth unbounded above and bounded below Swish activation function in our model. Property of unboundedness helps to avoid saturation while smoothing helps in optimization and generalization of the model. Performance of the proposed model is evaluated on five diverse datasets including CK+, JAFFE, FER-2013, KDEF and FERG datasets. We also performed cross-corpora evaluation to show the generalizability of our model. The proposed model achieves very high recognition rate for all datasets that proves the merit of the proposed framework for both the human facial images and stylized cartoon characters. Moreover, we conducted an ablation study with different variants of our model to prove its efficiency and effectiveness for emotions identification.