理解人脸识别系统遭受恶意攻击的脆弱性至关重要。以往研究聚焦于重建可突破目标验证系统的人脸图像，但即便在白盒场景下，简单重建的图像也无法准确表征身份信息，因此一旦人脸系统更新或更换，攻击就很容易失效。本文旨在重建能够对未见过的编码器实施人脸攻击迁移的人脸图像，我们将该问题命名为人脸重建迁移攻击（Face Reconstruction Transfer Attack，FRTA），并证明其可被建模为一个分布外（out-of-distribution，OOD）泛化问题。受其OOD特性启发，我们提出通过带伪目标的平均潜在搜索与无监督验证（Averaged Latent Search and Unsupervised Validation with pseudo target，ALSUV）方法来解决FRTA。为增强对OOD未见过编码器的重建攻击效果，ALSUV通过多重潜在优化、潜在优化轨迹平均以及带伪目标的无监督验证，搜索摊销生成器StyleGAN2的潜在变量来重建人脸。我们在广泛使用的人脸数据集上验证了该方法的有效性和泛化性，同时开展了大量消融实验以及视觉、定性和定量分析，源代码将公开发布。
英文摘要：
Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance. Previous works have focused on reconstructing face images that can penetrate a targeted verification system. Even in the white-box scenario, however, naively reconstructed images misrepresent the identity information, hence the attacks are easily neutralized once the face system is updated or changed. In this paper, we aim to reconstruct face images which are capable of transferring face attacks on unseen encoders. We term this problem as Face Reconstruction Transfer Attack (FRTA) and show that it can be formulated as an out-of-distribution (OOD) generalization problem. Inspired by its OOD nature, we propose to solve FRTA by Averaged Latent Search and Unsupervised Validation with pseudo target (ALSUV). To strengthen the reconstruction attack on OOD unseen encoders, ALSUV reconstructs the face by searching the latent of amortized generator StyleGAN2 through multiple latent optimization, latent optimization trajectory averaging, and unsupervised validation with a pseudo target. We demonstrate the efficacy and generalization of our method on widely used face datasets, accompanying it with extensive ablation studies and visually, qualitatively, and quantitatively analyses. The source code will be released.
Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation
Jinan University（暨南大学）；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Detecting Adversarial Faces Using Only Real Face Self-Perturbations
Huazhong University of Science and Technology（华中科技大学）；Google（谷歌）；Software Development Center, Industrial and Commercial Bank of China（中国工商银行软件开发中心）；Salesforce Research（Salesforce研究院）
Huazhong University of Science and Technology（华中科技大学）；Zagazig University（扎加齐格大学）
Face recognition is known to be vulnerable to adversarial face images. Existing works craft face adversarial images by indiscriminately changing a single attribute without being aware of the intrinsic attributes of the images. To this end, we propose a new Semantic Adversarial Attack called SAA-StarGAN that tampers with the significant facial attributes for each image. We predict the most significant attributes by applying the cosine similarity or probability score. The probability score method is based on training a Face Verification model for an attribute prediction task to obtain a class pr…
Compared to 2D face presentation attacks (e.g. printed photos and video replays), 3D type attacks are more challenging to face recognition systems (FRS) by presenting 3D characteristics or materials similar to real faces. Existing 3D face spoofing databases, however, mostly based on 3D masks, are restricted to small data size or poor authenticity due to the production difficulty and high cost. In this work, we introduce the first wax figure face database, WFFD, as one type of super-realistic 3D presentation attacks to spoof the FRS. This database consists of 2200 images with both real and wax …
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
Face masks have become one of the main methods for reducing the transmission of COVID-19. This makes face recognition (FR) a challenging task because masks hide several discriminative features of faces. Moreover, face presentation attack detection (PAD) is crucial to ensure the security of FR systems. In contrast to the growing number of masked FR studies, the impact of face masked attacks on PAD has not been explored. Therefore, we present novel attacks with real face masks placed on presentations and attacks with subjects wearing masks to reflect the current real-world situation. Furthermore…
University of Prishtina（普里什蒂纳大学）；University of Oslo（奥斯陆大学）
Biometric authentication methods, representing the "something you are" scheme, are considered the most secure approach for gaining access to protected resources. Recent attacks using Machine Learning techniques demand a serious systematic reevaluation of biometric authentication. This paper analyzes and presents the Fast Gradient Sign Method (FGSM) attack using face recognition for biometric authentication. Machine Learning techniques have been used to train and test the model, which can classify and identify different people's faces and which will be used as a target for carrying out the atta…
Beijing University of Posts and Telecommunications（北京邮电大学）
With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. So, it is important to study how face recognition networks are subject to attacks. In this paper, we focus on a novel way to do attacks against face recognition network that misleads the network to identify someone as the target person not misclassify inconspicuously. Simultaneously, for this purpose, we introduce a specific attentional adversarial attack generative network to generate fake face images. For capturing the semantic information of the target person, this work adds a conditional …
Face recognition has achieved considerable progress in recent years thanks to the development of deep neural networks, but it has recently been discovered that deep neural networks are vulnerable to adversarial examples. This means that face recognition models or systems based on deep neural networks are also susceptible to adversarial examples. However, the existing methods of attacking face recognition models or systems with adversarial examples can effectively complete white-box attacks but not black-box impersonation attacks, physical attacks, or convenient attacks, particularly on commerc…
In a typical face recognition pipeline, the task of the face detector is to localize the face region. However, the face detector localizes regions that look like a face, irrespective of the liveliness of the face, which makes the entire system susceptible to presentation attacks. In this work, we try to reformulate the task of the face detector to detect real faces, thus eliminating the threat of presentation attacks. While this task could be challenging with visible spectrum images alone, we leverage the multi-channel information available from off the shelf devices (such as color, depth, and…
Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）
Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the targeted DNN is always available, and an attacker can always inject a specific pattern to the training data to further fine-tune the DNN model. However, in practice, such attack may not be feasible as the DNN model is encrypted and only available to the secure enclave. In this paper, we propose a novel black-box backdoor attack technique on face recognition …
Recent successful adversarial attacks on face recognition show that, despite the remarkable progress of face recognition models, they are still far behind the human intelligence for perception and recognition. It reveals the vulnerability of deep convolutional neural networks (CNNs) as state-of-the-art building block for face recognition models against adversarial examples, which can cause certain consequences for secure systems. Gradient-based adversarial attacks are widely studied before and proved to be successful against face recognition models. However, finding the optimized perturbation …
Monash University（莫纳什大学）；Tencent AI Lab（腾讯AI Lab）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications. However, recent studies have shown that DNNs are very vulnerable to adversarial examples, raising serious concerns on the security of real-world face recognition. In this work, we study sticker-based physical attacks on face recognition for better understanding its adversarial robustness. To this end, we first analyze in-depth the complicated physical-world conditions confronted by attacking face recognition, including the different v…
Graduate University for Advanced Studies, SOKENDAI（综合研究大学院大学）；Idiap Research Institute（Idiap研究所）；National Institute of Informatics（国立情报学研究所）；SOKENDAI（综合研究大学院大学）；University of Tokyo（东京大学）
Face authentication is now widely used, especially on mobile devices, rather than authentication using a personal identification number or an unlock pattern, due to its convenience. It has thus become a tempting target for attackers using a presentation attack. Traditional presentation attacks use facial images or videos of the victim. Previous work has proven the existence of master faces, i.e., faces that match multiple enrolled templates in face recognition systems, and their existence extends the ability of presentation attacks. In this paper, we perform an extensive study on latent variab…
The Graduate University for Advanced Studies, SOKENDAI（综合研究大学院大学）；National Institute of Informatics（国立信息学研究所）；The University of Edinburgh（爱丁堡大学）；The University of Tokyo（东京大学）；Idiap Research Institute（Idiap研究所）
Due to its convenience, biometric authentication, especial face authentication, has become increasingly mainstream and thus is now a prime target for attackers. Presentation attacks and face morphing are typical types of attack. Previous research has shown that finger-vein- and fingerprint-based authentication methods are susceptible to wolf attacks, in which a wolf sample matches many enrolled user templates. In this work, we demonstrated that wolf (generic) faces, which we call "master faces," can also compromise face recognition systems and that the master face concept can be generalized in…
Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications. Despite the enhanced accuracies, robustness of these algorithms against attacks and bias has been challenged. This paper summarizes different ways in which the robustness of a face recognition algorithm is challenged, which can severely affect its intended working. Different types of attacks such as physical presentation attacks, disguise/makeup, digital adversarial attacks, and morphing/tampering using GANs have been discussed. We also present a discussion on th…
With the rapid progress over the past five years, face authentication has become the most pervasive biometric recognition method. Thanks to the high-accuracy recognition performance and user-friendly usage, automatic face recognition (AFR) has exploded into a plethora of practical applications over device unlocking, checking-in, and financial payment. In spite of the tremendous success of face authentication, a variety of face presentation attacks (FPA), such as print attacks, replay attacks, and 3D mask attacks, have raised pressing mistrust concerns. Besides physical face attacks, face video…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks. Previous model-based and deep learning approaches achieve satisfactory performance for 2D face spoofs, but remain limited for more advanced 3D attacks such as vivid masks. In this paper, we address 3D face anti-spoofing via the proposed Hypergraph Convolutional Neural Networks (HGCNN). Firstly, we construct a computation-efficient and posture-invariant face representation with only a few key points on hypergraphs. The hypergraph representation is then fed into the designed HGCNN with hypergraph…
Rounding confidence score is considered trivial but a simple and effective countermeasure to stop gradient descent based image reconstruction attacks. However, its capability in the face of more sophisticated reconstruction attacks is an uninvestigated research area. In this paper, we prove that, the face reconstruction attacks based on composite faces can reveal the inefficiency of rounding policy as countermeasure. We assume that, the attacker takes advantage of face composite parts which helps the attacker to get access to the most important features of the face or decompose it to the indep…
Fraunhofer Institute for Computer Graphics Research（弗劳恩霍夫计算机图形学研究所）；TU Darmstadt（达姆施塔特工业大学）
Morphing attacks are a form of presentation attacks that gathered increasing attention in recent years. A morphed image can be successfully verified to multiple identities. This operation, therefore, poses serious security issues related to the ability of a travel or identity document to be verified to belong to multiple persons. Previous works touched on the issue of the quality of morphing attack images, however, with the main goal of quantitatively proofing the realistic appearance of the produced morphing attacks. We theorize that the morphing processes might have an effect on both, the pe…
Face anti-spoofing is designed to keep face recognition systems from recognizing fake faces as the genuine users. While advanced face anti-spoofing methods are developed, new types of spoof attacks are also being created and becoming a threat to all existing systems. We define the detection of unknown spoof attacks as Zero-Shot Face Anti-spoofing (ZSFA). Previous works of ZSFA only study 1-2 types of spoof attacks, such as print/replay attacks, which limits the insight of this problem. In this work, we expand the ZSFA problem to a wide range of 13 types of spoof attacks, including print attack…
Cujo AI and Adversa AI hosted the MLSec face recognition challenge. The goal was to attack a black box face recognition model with targeted attacks. The model returned the confidence of the target class and a stealthiness score. For an attack to be considered successful the target class has to have the highest confidence among all classes and the stealthiness has to be at least 0.5. In our approach we paste the face of a target into a source image. By utilizing position, scaling, rotation and transparency attributes we reached 3rd place. Our approach took approximately 200 queries per attack f…
Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models. In this work, instead of performing perturbations on the low-level pixels, we propose to generate attacks through perturbing on the high-level semantics to improve attack transfera…
The modern open internet contains billions of public images of human faces across the web, especially on social media websites used by half the world's population. In this context, Face Recognition (FR) systems have the potential to match faces to specific names and identities, creating glaring privacy concerns. Adversarial attacks are a promising way to grant users privacy from FR systems by disrupting their capability to recognize faces. Yet, such attacks can be perceptible to human observers, especially under the more challenging black-box threat model. In the literature, the justification …
Fraunhofer HHI（弗劳恩霍夫电信研究所）；Humboldt University Berlin（柏林洪堡大学）
Artificial neural networks tend to learn only what they need for a task. A manipulation of the training data can counter this phenomenon. In this paper, we study the effect of different alterations of the training data, which limit the amount and position of information that is available for the decision making. We analyze the accuracy and robustness against semantic and black box attacks on the networks that were trained on different training data modifications for the particular example of morphing attacks. A morphing attack is an attack on a biometric facial recognition system where the sys…
Norwegian University of Science and Technology (NTNU)（挪威科技大学）；AiBA AS（AiBA公司）；Indian Institute of Technology (IIT), Mandi（印度理工学院曼迪分校）；MOBAI AS（MOBAI公司）
Face morphing attacks have emerged as a potential threat, particularly in automatic border control scenarios. Morphing attacks permit more than one individual to use travel documents that can be used to cross borders using automatic border control gates. The potential for morphing attacks depends on the selection of data subjects (accomplice and malicious actors). This work investigates lookalike and identical twins as the source of face morphing generation. We present a systematic study on benchmarking the vulnerability of Face Recognition Systems (FRS) to lookalike and identical twin morphin…
Hong Kong Baptist University（香港浸会大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input distributions and different types of spoof attacks. In reality, training data (both real face images and spoof images) are not directly shared between data owners due to legal and privacy issues. In this paper, with the motivation of circumventing this challenge, we propose Federated Face Presentation Attack Detection (FedPAD) framework. FedPAD simulta…
School of Electronics and Information, Northwestern Polytechnical University（西北工业大学电子信息学院）；Department of Electrical and Electronic Engineering, University of Cagliari（卡利亚里大学电气与电子工程系）
Face presentation attacks have become a major threat to face recognition systems and many countermeasures have been proposed in the past decade. However, most of them are devoted to 2D face presentation attacks, rather than 3D face masks. Unlike the real face, the 3D face mask is usually made of resin materials and has a smooth surface, resulting in reflectance differences. So, we propose a novel detection method for 3D face mask presentation attack by modeling reflectance differences based on intrinsic image analysis. In the proposed method, the face image is first processed with intrinsic im…
Nanyang Technological University（南洋理工大学）；SailYond Technology（赛扬科技）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）
Face recognition technology has been widely used in daily interactive applications such as checking-in and mobile payment due to its convenience and high accuracy. However, its vulnerability to presentation attacks (PAs) limits its reliable use in ultra-secure applicational scenarios. A presentation attack is first defined in ISO standard as: a presentation to the biometric data capture subsystem with the goal of interfering with the operation of the biometric system. Specifically, PAs range from simple 2D print, replay and more sophisticated 3D masks and partial masks. To defend the face reco…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
Wearing a mask has proven to be one of the most effective ways to prevent the transmission of SARS-CoV-2 coronavirus. However, wearing a mask poses challenges for different face recognition tasks and raises concerns about the performance of masked face presentation detection (PAD). The main issues facing the mask face PAD are the wrongly classified bona fide masked faces and the wrongly classified partial attacks (covered by real masks). This work addresses these issues by proposing a method that considers partial attack labels to supervise the PAD model training, as well as regional weighted …
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Youtu Lab, Tencent（腾讯优图实验室）；Fudan University（复旦大学）
Deep neural networks, particularly face recognition models, have been shown to be vulnerable to both digital and physical adversarial examples. However, existing adversarial examples against face recognition systems either lack transferability to black-box models, or fail to be implemented in practice. In this paper, we propose a unified adversarial face generation method - Adv-Makeup, which can realize imperceptible and transferable attack under black-box setting. Adv-Makeup develops a task-driven makeup generation method with the blending module to synthesize imperceptible eye shadow over th…
Face-morphing attacks have been a cause for concern for a number of years. Striving to remain one step ahead of attackers, researchers have proposed many methods of both creating and detecting morphed images. These detection methods, however, have generally proven to be inadequate. In this work we identify two new, GAN-based methods that an attacker may already have in his arsenal. Each method is evaluated against state-of-the-art facial recognition (FR) algorithms and we demonstrate that improvements to the fidelity of FR algorithms do lead to a reduction in the success rate of attacks provid…
School of Information Technology, Monash University Malaysia（蒙纳士大学马来西亚校区信息技术学院）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Faculty of Computer Science and Technology, Wenzhou University（温州大学计算机科学与技术学院）；Monash Suzhou Research Institute（蒙纳士苏州研究院）；Department of Data Science and AI, Monash University（蒙纳士大学数据科学与人工智能系）；The University of Sassari（萨萨里大学）
The majority of adversarial attack techniques perform well against deep face recognition when the full knowledge of the system is revealed (\emph{white-box}). However, such techniques act unsuccessfully in the gray-box setting where the face templates are unknown to the attackers. In this work, we propose a similarity-based gray-box adversarial attack (SGADV) technique with a newly developed objective function. SGADV utilizes the dissimilarity score to produce the optimized adversarial example, i.e., similarity-based adversarial attack. This technique applies to both white-box and gray-box att…
Universidad Autonoma de Madrid（马德里自治大学）；European Commission - DG Joint Research Centre（欧盟委员会联合研究中心）
The main scope of this chapter is to serve as an introduction to face presentation attack detection, including key resources and advances in the field in the last few years. The next pages present the different presentation attacks that a face recognition system can confront, in which an attacker presents to the sensor, mainly a camera, a Presentation Attack Instrument (PAI), that is generally a photograph, a video, or a mask, to try to impersonate a genuine user. First, we make an introduction of the current status of face recognition, its level of deployment, and its challenges. In addition,…
Norwegian University of Science and Technology（挪威科技大学）；Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形学研究所）；Technical University of Darmstadt（达姆施塔特工业大学）
A MasterFace is a face image that can successfully match against a large portion of the population. Since their generation does not require access to the information of the enrolled subjects, MasterFace attacks represent a potential security risk for widely-used face recognition systems. Previous works proposed methods for generating such images and demonstrated that these attacks can strongly compromise face recognition. However, previous works followed evaluation settings consisting of older recognition models, limited cross-dataset and cross-model evaluations, and the use of low-scale testi…
Face presentation attack detection (PAD) is an essential measure to protect face recognition systems from being spoofed by malicious users and has attracted great attention from both academia and industry. Although most of the existing methods can achieve desired performance to some extent, the generalization issue of face presentation attack detection under cross-domain settings (e.g., the setting of unseen attacks and varying illumination) remains to be solved. In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-mo…
Sichuan University（四川大学）；Michigan State University（密歇根州立大学）
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously. Unlike existing 3D face reconstruction methods, our proposed method directly regresses dense 3D face shapes from single 2D images, and tackles identity and residual (i.e., non-identity) components in 3D face shapes explicitly and separately based on a composite 3D face shape model with latent representation…
Norwegian University of Science and Technology（挪威科技大学）
Face Recognition Systems (FRS) are vulnerable to various attacks performed directly and indirectly. Among these attacks, face morphing attacks are highly potential in deceiving automatic FRS and human observers and indicate a severe security threat, especially in the border control scenario. This work presents a face morphing attack detection, especially in the On-The-Fly (OTF) Automatic Border Control (ABC) scenario. We present a novel Differential-MAD (D-MAD) algorithm based on the spherical interpolation and hierarchical fusion of deep features computed from six different pre-trained deep C…
Find the Differences: Differential Morphing Attack Detection vs Face Recognition
Data Management and Biometrics, University of Twente, Enschede, the Netherlands（数据管理与生物特征识别，特文特大学，埃舍德，荷兰）；Machine Learning and Data Engineering, University of Münster, Münster, Germany（机器学习与数据工程，明斯特大学，明斯特，德国）
Institute of Artificial Intelligence and Robotics for Society（人工智能与数字经济广东省实验室（深圳））；Norwegian University of Science and Technology（挪威科技大学）；Shenzhen University（深圳大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
The robustness and generalization ability of Presentation Attack Detection (PAD) methods is critical to ensure the security of Face Recognition Systems (FRSs). However, in a real scenario, Presentation Attacks (PAs) are various and it is hard to predict the Presentation Attack Instrument (PAI) species that will be used by the attacker. Existing PAD methods are highly dependent on the limited training set and cannot generalize well to unknown PAI species. Unlike this specific PAD task, other face related tasks trained by huge amount of real faces (e.g. face recognition and attribute editing) ca…
Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, JLU（教育部符号计算与知识工程重点实验室）；Department of Computer Science and Software Engineering, The University of Western Australia（西澳大学计算机科学与软件工程系）
