Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal

Costa‐Pazo, Artur; Jiménez‐Cabello, David; Vázquez-Fernández, Esteban; Alba-Castro, José Luis; López-Sastre, Roberto J.

doi:10.1109/icb45273.2019.8987290

Cited by 20 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from the last column in Table 3 that several kinds of multi-modal fusion strategies (e.g., input-level data fusion, feature-level squeeze and excitation (SE) [26] fusion and score-level fusion) were used. In terms of the pre-training data, two teams (VisionLabs and Gradi-antResearch) leveraged pre-trained models from related face analysis tasks (e.g., face recognition models on CASIA-WebFace [78] and face PAD models on GRAD-GPAD [11]) to mitigate the issues with overfitting. It is worth to note that all three top-performing solutions (VisionLabs, ReadSense and Feather) adopted ensemble strategy to aggregate the predictions from multiple variant models.…”

Section: Resultsmentioning

confidence: 99%

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%

Review of Face Presentation Attack Detection Competitions

Yu¹,

Komulainen²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There is growing interest in generalizing detectors to enable them to handle unseen attacks [45]. This is a difficult but important effort since the number of attack techniques and their variances have been increasing rapidly.…”

Section: Presentation Attack Detectionmentioning

confidence: 99%

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Nguyen

Yamagishi

Echizen

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

462

224

View full text Add to dashboard Cite

The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intelligence algorithms. In addition to their many beneficial applications in daily life and business, computergenerated/manipulated images and videos can be used for malicious purposes that violate security systems, privacy, and social trust. The deepfake phenomenon and its variations enable a normal user to use his or her personal computer to easily create fake videos of anybody from a short real online video. Several countermeasures have been introduced to deal with attacks using such videos. However, most of them are targeted at certain domains and are ineffective when applied to other domains or new attacks. In this paper, we introduce a capsule network that can detect various kinds of attacks, from presentation attacks using printed images and replayed videos to attacks using fake videos created using deep learning. It uses many fewer parameters than traditional convolutional neural networks with similar performance. Moreover, we explain, for the first time ever in the literature, the theory behind the application of capsule networks to the forensics problem through detailed analysis and visualization.

show abstract

“…Also, the extended F I G U R E 3 Sex distribution of extended GRAD-GPAD datasets GRAD-GPAD v2 dataset allows a better statistical significance of the results of previous protocols, leveraging their added-value for assessing face-PAD generalisation on current and future algorithms. In addition to former protocols presented in [8,31] (Grandtest, Cross-Dataset, One-PAI, Cross-PAI or Unseen-Attack, Cross-Device, Cross-FaceResolution, Cross-Condition and Lifelong-Learning), two novel groups of protocols are introduced in this version: the Leave-Other-Dataset-Out (LODO) and the Demographics protocols.…”

Section: Protocolsmentioning

confidence: 99%

“…In GRAD-GPAD v0 [8], seven protocols were presented, some based on classical assessments and others with new approaches. Then, GRAD-GPAD v1 [31] added a lifelonglearning protocol over the 10 available datasets (domains).…”

Section: Orcidmentioning

confidence: 99%

“…However, despite the fact that using larger datasets leads to better performance, it is not yet sufficient to solve the generalisation issue in a real production environment. In [8], the authors introduced the largest aggregated datasets so far, the GRAD‐GPAD framework. In this evaluation framework, the authors incorporated the 10 most representative face‐PAD datasets (CASIA, Replay‐Attack, 3DMAD [28], MSU‐MFSD, Replay‐Mobile, HKBU v1 [29], Oulu‐NPU [27], Rose‐Youtu [14], SiW [15], and CS‐MAD [30]), presenting a set of protocols to evaluate generalisation from different angles.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Face presentation attack detection. A comprehensive evaluation of the generalisation problem

et al. 2021

View full text Add to dashboard Cite

Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face-PAD) is a key component in providing trustable facial access to digital devices. Despite the success of several face-PAD works in publicly available datasets, most of them fail to reach the market, revealing the lack of evaluation frameworks that represent realistic settings. Here, an extensive analysis of the generalisation problem in face-PAD is provided, jointly with an evaluation strategy based on the aggregation of most publicly available datasets and a set of novel protocols to cover the most realistic settings, including a novel demographic bias analysis. Besides, a new finegrained categorisation of presentation attacks and instruments is provided, enabling higher flexibility in assessing the generalisation of different algorithms under a common framework. As a result, GRAD-GPAD v2, a comprehensive and modular framework is presented to evaluate the performance of face-PAD approaches in realistic settings, enabling accountability and fair comparison of most face-PAD approaches in the literature.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal

Cited by 20 publications

References 29 publications

Review of Face Presentation Attack Detection Competitions

Review of Face Presentation Attack Detection Competitions

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Face presentation attack detection. A comprehensive evaluation of the generalisation problem

Contact Info

Product

Resources

About