Antispoofing in face biometrics: a comprehensive study on software-based techniques

Abstract

The vulnerability of the face recognition system to spoofing attacks has piqued the biometric community's interest, motivating them to develop anti-spoofing techniques to secure it. Photo, video, or mask attacks can compromise face biometric systems (types of presentation attacks). Spoofing attacks are detected using liveness detection techniques, which determine whether the facial image presented at a biometric system is a live face or a fake version of it. We discuss the classification of face anti-spoofing techniques in this paper. Anti-spoofing techniques are divided into two categories: hardware and software methods. Hardware-based techniques are summarized briefly. A comprehensive study on software-based countermeasures for presentation attacks is discussed, which are further divided into static and dynamic methods. We cited a few publicly available presentation attack datasets and calculated a few metrics to demonstrate the value of anti-spoofing techniques.

Awareness of the Anti-Photo and Video Voyeurism Act of 2009 (Ra 9995) in Selected Universities in Palawan

“…Awareness on Anti-Photo and Video Voyeurism Act of 2009 replays to enhance detection capabilities (Vinutha & Thippeswamy, 2023). The development of antispoofing algorithms based on image fusion and spatial frequency descriptors demonstrates ongoing research in computer science to address these privacy breaches (Yu et al, 2021;Ali & Park, 2019).…”

Deepfake Video Detection Using Res-Next CNN and LSTM

“…Initially, the films were obtained from a dataset consisting of three sources [1]. DFDC [3] CELEB DF [2] FF++ Lastly, we have our own self-created dataset [4] that we employ to enhance training accuracy and produce real-time video results. Additionally, we combined the several datasets to produce a brand-new dataset.…”

“…After processing of the DFDC dataset, we have taken 800 Real and 500 Fake videos from the DFDC [2] dataset. 890 Real and 1400 Fake videos from the Celeb-DF [3] dataset then 310 Real and 100 fake from Self-created dataset [4]. [2] dataset.…”

“…[2] dataset. 890 Real and 1400 Fake videos from the Celeb-DF [3] dataset then 310 Real and 100 fake from Self-created dataset [4]. Which makes our total dataset consisting 3000 Real, 3000 fake videos and 6000 videos in total.…”

“…They are able to spot irregularities in the video's visual material, like strange facial expressions and distortions. [4] Recurrent Neural Networks (RNNs): RNNs can be used to assess the audio content of the video and are frequently employed for sequence analysis. They are able to detect irregularities in tone, pitch, and cadence in the audio.…”