A face antispoofing database with diverse attacks

By Zhiwei Zhang, Junjie Yan, Sifei Liu, Zhen Lei, Dong Yi, S. Li. 2012

870 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Robust multimodal face and fingerprint fusion in the presence of spoofing attacks (2016, background): “CASIA AntispoofingFace [38]: This database of 600 clips of 50 clients with 640 480 pixels resolution comes with 3 genuine and 9 fake samples per user, offering low, medium and high quality setups and 3 fake attacks.”
Learn Convolutional Neural Network for Face Anti-Spoofing (2014, methodology): “In the experiments, over 70% relative decrease of Half Total Error Rate (HTER) is achieved on two challenging datasets, CASIA [36] and REPLAY-ATTACK [7] compared with the -state-ofthe-art.”
Deep Tree Learning for Zero-Shot Face Anti-Spoofing (2019, methodology): “Also, we test on previous face anti-spoofing databases, including CASIA [50], Replay-Attack [15], and MSU-MFSD [42]), compare with the state of the art.”
Face Spoofing Detection Using Colour Texture Analysis (2016, background): “One can assume that fake faces are usually smaller in size or they would contain fewer high frequency components compared to genuine ones, thus countermeasures based on analysing the high frequency content have been proposed [2]–[4].”
LBP − T OP based countermeasure against face spooﬁng attacks (2012, methodology): “Evaluations carried out with three different databases, the NUAA Photograph Impostor Database, REPLAY ATTACK database and CASIA - Face Anti-spoofing Database [24] showed a good discrimination power with HTER equals to 15.”
Face liveness detection with component dependent descriptor (2013, methodology): “The ﬁrst row is NUAA database [24], the second is PRINT-ATTACK database [1], and the third is CASIA database [25]. ble to inaccuracy detection or tracking on face components.”
Secure Face Unlock: Spoof Detection on Smartphones (2016, methodology): “We perform these tests using the protocols specified in [7], [20], and [40] as well as a protocol we define to simulate smartphone spoof attacks.”
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection (2019, background): “Sample frames from CASIA-MFSD [35], Idiap Replay-Attack [8], MSU-MFSD [31], and Oulu-NPU [4] datasets.”
Face De-Spoofing: Anti-Spoofing via Noise Modeling (2018, methodology): “5, our method achieves the competitive performance on the cross testing from CASIA-MFSD to Replay-Attack.”
Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect (2013, background): “In [21] Zhang et al. state that massive usage of masks does not exist in the literature, mainly due to the fact that it is too expensive to produce client-like masks.”
Face Anti-Spoofing: Model Matters, so Does Data (2019, methodology): “Besides, existing datasets for face antispoofing including NUAA [37], CASIA-MFSD [44], and Replay-Attack [11] were released years ago.”
Deep Face Recognition: A Survey (2018, neutral): “anti-attack (CASIA-FASD [210]) and 3D FR (Bosphorus [203], BU-3DFE [205] and FRGCv2 [206]).”
Single-Side Domain Generalization for Face Anti-Spoofing (2020, methodology): “Four public face anti-spoofing databases are utilized to evaluate the effectiveness of our method: OULUNPU [7] (denoted as O), CASIA-FASD [45] (denoted as C), Idiap Replay-Attack [8] (denoted as I), and MSU-MFSD [39] (denoted as M).”
Face Recognition on Consumer Devices: Reflections on Replay Attacks (2015, background): “The closest datasets (such as REPLAY-ATTACK [13] and CASIA-FASD [44]) are designed to detect live people versus spoofing attempts (Type 1 attacks in Figure 1), but they do not (and cannot) attempt to validate that the biometric data was captured in real-time (Type 2 attacks in Figure 1).”
Face Biometrics Under Spoofing Attacks: Vulnerabilities, Countermeasures, Open Issues, and Research Directions (2014, background): “photographs and videos displayed through a tablet screen [31].”
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision (2018, methodology): “Existing face anti-spooﬁng databases, such as NUAA [43], CASIA [50], Replay-Attack [17], and MSU-MFSD [45], were collected 3 − 5 years ago.”