Unified Detection of Digital and Physical Face Attacks

Deb, Debayan; Liu, Xiaoming; Jain, Anil K.

doi:10.48550/arxiv.2104.02156

Cited by 5 publications

(8 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Solutions of the unimodal (colour) track: Table 8 summarizes the face PAD solutions of the teams participated in the unimodal track. The source codes of ten teams, including VisionLabs 10 , BOBO 11 , Harvest 12 , ZhangTT 13 , Newlandtianyan 14 , Dopamine 15 , IecLab 16 , Chungwa-Telecom 17 , Wgqtmac 18 , and Hulking 19 were made publicly available. It was not surprising that every team adopted end-toend learning based approaches due to the strong representation capacity of modern deep models.…”

Section: Resultsmentioning

confidence: 99%

“…Despite the differences in generation techniques and visual quality, some of these attacks still have coherent properties and artefacts. In [13], a unified digital and physical face attack detection framework is proposed to learn joint representations for coherent attacks. Therefore, another interesting challenge to tackle in upcoming contests as-sessing the robustness of face biometric systems would be to simultaneously detect both digital and physical attacks.…”

Section: Future Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Review of Face Presentation Attack Detection Competitions

Yu¹,

Komulainen²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Face presentation attack detection (PAD) has received increasing attention ever since the vulnerabilities to spoofing have been widely recognized. The state of the art in unimodal and multi-modal face anti-spoofing has been assessed in eight international competitions organized in conjunction with major biometrics and computer vision conferences in 2011, 2013, 2017, 2019, 2020 and 2021, each introducing new challenges to the research community. In this chapter, we present the design and results of the five latest competitions from 2019 until 2021. The first two challenges aimed to evaluate the effectiveness of face PAD in multi-modal setup introducing near-infrared (NIR) and depth modalities in addition to colour camera data, while the latest three competitions focused on evaluating domain and attack type generalization abilities of face PAD algorithms operating on conventional colour images and videos. We also discuss the lessons learnt from the competitions and future challenges in the field in general.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Future Challengesmentioning

confidence: 99%

Review of Face Presentation Attack Detection Competitions

Yu¹,

Komulainen²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast to hardware-based methods, software-based techniques have been proposed to spot attacks in the physical and digital domain. In general, the existing detection schemes use i) texture analysis [13], ii) digital forensics [23], or iii) deep-learning techniques [14], [11].…”

Section: Related Workmentioning

confidence: 99%

“…Mehta et al [25] proposed an algorithm that showed promising detection results on three PAI species in the physical domain (silicone mask, photo-, and video-replay attacks) and one attack in the digital domain (face swap). In [11], Deb et al proposed a multi-task learning framework with k-means clustering, which showed high detection accuracy (∼94.73%) on a database comprising 25 attack types across three different attack categories (adversarial, digital, and physical).…”

Section: Related Workmentioning

confidence: 99%

“…Identity attacks are not only a concern from a security point-of-view and when used in biometric systems, but also in general media forensics, since digital identity attacks can be used to spread misinformation (e.g., the so-called DeepFakes) [9], [3]. To address the aforementioned concerns, several identity attack detection techniques have been proposed in the literature [10], [11], [12], [13], [14]. Generally, most of those approaches consider attack detection as a bi-class classification problem where classifiers are trained on both bona fide presentations (BPs) and attack presentations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Differential Anomaly Detection for Facial Images

Ibsen¹,

Gonzalez-Soler²,

Rathgeb³

et al. 2021

Preprint

View full text Add to dashboard Cite

Due to their convenience and high accuracy, face recognition systems are widely employed in governmental and personal security applications to automatically recognise individuals. Despite recent advances, face recognition systems have shown to be particularly vulnerable to identity attacks (i.e., digital manipulations and attack presentations). Identity attacks pose a big security threat as they can be used to gain unauthorised access and spread misinformation. In this context, most algorithms for detecting identity attacks generalise poorly to attack types that are unknown at training time. To tackle this problem, we introduce a differential anomaly detection framework in which deep face embeddings are first extracted from pairs of images (i.e., reference and probe) and then combined for identity attack detection. The experimental evaluation conducted over several databases shows a high generalisation capability of the proposed method for detecting unknown attacks in both the digital and physical domains.

show abstract

Deep Learning for Face Anti-Spoofing: A Survey

Qin

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Face anti-spoofing (FAS) has lately attracted increasing attention due to its vital role in securing face recognition systems from presentation attacks (PAs). As more and more realistic PAs with novel types spring up, early-stage FAS methods based on handcrafted features become unreliable due to their limited representation capacity. With the emergence of large-scale academic datasets in the recent decade, deep learning based FAS achieves remarkable performance and dominates this area. However, existing reviews in this field mainly focus on the handcrafted features, which are outdated and uninspiring for the progress of FAS community. In this paper, to stimulate future research, we present the first comprehensive review of recent advances in deep learning based FAS. It covers several novel and insightful components: 1) besides supervision with binary label (e.g., '0' for bonafide vs. '1' for PAs), we also investigate recent methods with pixel-wise supervision (e.g., pseudo depth map); 2) in addition to traditional intra-dataset evaluation, we collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, we summarize the deep learning applications under multi-modal (e.g., depth and infrared) or specialized (e.g., light field and flash) sensors. We conclude this survey by emphasizing current open issues and highlighting potential prospects.

show abstract

Unified Detection of Digital and Physical Face Attacks

Cited by 5 publications

References 57 publications

Review of Face Presentation Attack Detection Competitions

Review of Face Presentation Attack Detection Competitions

Differential Anomaly Detection for Facial Images

Deep Learning for Face Anti-Spoofing: A Survey

Contact Info

Product

Resources

About