Active Facial Liveness Detection

Brief Overview

Active facial liveness detection rivals the passive detection type, but many experts see it as an obsolete security measure.

Face recognition systems have been widely used since at least 2002: during the Super Bowl, this technology was put to a test by law enforcement agencies (even though it returned unsatisfactory results). The issue of liveness was first addressed by Dorothy E. Denning in her article It's "liveness", not secrecy, that counts. The idea was that a system should be able to check if the accessor is actually a living person and not his/her lifeless substitute: a photo, mask or a sculpture. Active facial liveness detection predates passive detection. In essence, it is challenge-based, prompting a person to perform a certain task like smile, blink, turn their head, follow an on-screen object with their eyes, and so on.

Dorothy E. Denning, author of the liveness concept

However, malicious actors soon learned to overcome the barriers set by the active liveness check. A rich repertoire of crime tools was developed — from eye-holed masks to sophisticated face swap animations. Moreover, the active liveness method is known to cause friction to the verification process. It can be compared to entering a password or solving a captcha puzzle. This friction factor leads to "customer frustration" and can result in verification abandonment. As a result, a "successor system" was designed based on passive liveness detection. While it appears more flexible and user-friendly, it also remains vulnerable to spoofing attacks that mimic the liveness factor.

Liveness Indicators

It is logically assumed that a fake face presents characteristics that are unnatural to a human face. Based on this assumption experts highlight the following liveness indicators.

Texture analysis

By default, an artificial face would present unnatural texture patterns. Texture analysis aims to extract features from the presented face to identify their "naturalness". This analysis includes three categories used in passive and active liveness solutions:

Parameters. This involves Image Quality Assessment (IQA), which serves to spot errors in the input visual data. The parameters that undergo analysis include Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Normalized Absolute Error (NAE), Total Edge Difference (TED), and others.

IQA assessment table

Dynamic texture. This method is based on detecting spatio-temporal Local Binary Patterns (LPB). It’s used for inspecting facial structure with the additional assistance from the Three Orthogonal Planes (TOP) parameter.

Three Orthogonal Planes graphic depiction

Static texture analysis. This method depends on analyzing gray scale and color textures, as well as indexing the values for the planes.

Currently, texture analysis is considered by experts to have great potential in both passive and active liveness detection.

Motion analysis

It is estimated that flat or planar objects — like a printed cutout — move differently than a 3D human face. Generally, speaking, motion analysis implies the calculation of information regarding the moving points of an image in the scene, as written here.

There are three main elements in this technique:

Focus distance-based. It includes the Depth of Field (DOF) parameter, which is used for detecting the distance between the closest and the farthest objects in the image. Thus, the camera focus and illumination can testify that the image belongs to a bona fide user.

Optical flow-based. This method calculates the optical flow by creating an image frame sequence. Every single frame is converted into vector data, In turn, this allows to pixel directions and velocity motion between every frame.

Scenic clues-based. In this approach three scenic clues are studied. Non-rigid motion clue pays attention to blinking, lip movement, wrinkling, etc. Face-background consistency implies that motion of both face and background can vary in consistency: high for fake images and low for pristine. At the same time, imaging banding effect indicates that fake images will display certain defects. Scenic clues-based analysis employs such tools as GMM-based motion detection method, wavelet decomposition, and image alignment based on low-rank matrix decomposition.

Life sign indicators

This approach, widely used in active liveness systems, echoes scenic clues-based analysis. For instance, it pays attention to blinking as a categorical life sign. This technique analyzes a sequence of input images to firstly, detect eyes and secondly, calculate eye region variations. As a result, the active liveness system can accurately tell whether the person is real or not. Another major life sign is the mouth state. Conditional Random Fields (CRMs) and various types of discriminative models are used to determine whether the images are fake or genuine by studying lip movement.

3D properties

As a 3D object, the human face is supposed to have certain depth, as well as curvature. This technique can acquire visual data to detect whether the object lacks surface variation — a value that a real face will display.

The following formula is used in this method:

[math]\displaystyle{ C=\frac{(p-b)*v}{d^2} }[/math]

Transcript:

C — value of the curvature.
d — the mean distance of all points within Ωr
p — point of approximation of the actual curvature value.
v — eigenvector corresponding to the smallest eigenvalue of the decomposition.
b — baricenter of the Cartesian coordinates of the points within Ωr (spherical neighborhood)

Typically, the mean curvature retrieved from a human face is bigger than that calculated from a fake image. This can serve as a benchmark to identify fake faces.

3D acquisition from a photo (left) and a human face (right)

Content-based Analysis

Content-based analysis, that can be used in active liveness detection, is a promising technique and employs upper-body (UB) and a spoofing medium (SM) detectors. They in turn rely on Histogram of Oriented Gradient (HOG) descriptors, as well as linear support vector machines (SVM). The idea behind this approach is that a person can spot fake media using the context and scenery presented. Thus, the algorithm analyzes the scenic cues of a video, such as face/shoulders/torso alignment. It is trained with a dataset of deepfake videos and showed impressive results: 3.3% - 6.8% error rate.

Morphological Operations-based Analysis

This active liveness detection method studies opening/closing of the subject’s profile silhouette. Profile shapes are used for creating vector data. The technique also employs face rankings based on the Euclidean distances, and so on.

Other Indicators

Other known liveness indicators mostly involve combinations of the above-mentioned methods. More literature on the topic can be found here.

Disadvantages of Active Facial Liveness Detection

As discussed previously, active facial liveness detection has a number of weaknesses including attack vulnerabilities, increased customer friction, additional expenses, and so on. Researchers highlight the following major disadvantages of the active liveness detection:

Poor customer experience

Statistics show that at least 18% of clients abandon their carts due to active liveness detection which makes the checkout procedure lengthy. Another example indicates that 40% of customers stop the on-boarding process in the retail banking sphere because of the same reason. If used commercially, active liveness detection can significantly increase the wait time. In turn, this will undermine overall customer satisfaction.

Complicated process

Active liveness detection approach requires additional software to be installed on the user’s gizmo. It also needs more data capacity to send the captured images to the servers for further analysis. Therefore, an active liveness detection system may pose challenges in areas where Internet connection is poor or costly.

Vulnerabilities

Con artists have adapted to spoof active liveness detection using various techniques. They use Presentation Attack Instruments (PAIs) that vary in quality and ingenuity: from printed photos to elaborate silicone masks and deepfake generators.

Lack of standardization

Active liveness detection has no generally accepted industry standards. This implies that every company or institution faces their own challenges to verify a person and requires unique countermeasures when applying an active liveness check.

Attempts to Bypass Active Facial Liveness

Impostors can bypass a challenge-based system with various tools. These include:

An app like Face Swap Live.
2D and 3D masks with empty eyeholes.
A deepfake with the target’s face performing a required task.

A believable silicone mask with eyeholes

As long as a PAI allows a person to blink, rotate head, smile or move eyes, there’s a chance that the attack against the active system will be successful.

Creating a 3D image from a dataset of 2D photos

An interesting experiment was held at the university of North Carolina. It showed that it is possible to create a synthetic 3D face model, using a collection of photos of any given person. This involves transferring the facial texture, gaze correction, animations for creating facial expressions, and so on.

FAQ

What is active liveness detection?

Active liveness detection requires a person to execute a certain action to get verified.

Active liveness detection is a type of biometric identification, which prompts a person to do a specific action: blink, utter a password, make a gesture, etc. in order to be identified. Active detection is often criticized for its lengthy and awkward mode of operation. Compared to passive detection, active detection is believed to be is less suitable for client-oriented businesses. The key challenge is the higher wait time imposed by the detection system before a user can access the service. Nevertheless, active detection can be highly useful as an extra security layer. It is also indispensable in certain scenarios involving sensitive data.

What are the main liveness indicators?

A number of indicators are proposed to detect whether a presented face belongs to a live human or not.

Liveness detection and antispoofing have their own standards and metrics. Among the liveness indicators we can find:

Texture. By analyzing dynamic and static texture together with the image quality, it is possible to detect fake media.
Motion. This analysis provides vital data such as Depth of Field parameters, optical flow data and various scenic clues like facial expressions.
Life signs. It focuses on signals — such as blinking — to confirm that a target is alive.
3D properties. Explores depth/curvature of a face.
Context. Scenery, background, and context of media presented can also reveal a fake face.

Other indicators are mostly combinations of the ones mentioned above.

What is the main difference between active and passive facial liveness detection?

Passive approach offers a simpler and quicker identification process.

Passive method is cited by many as a better solution when compared to active facial liveness detection.

Active approach relies on the challenge-response system. It means that a person needs to perform a certain task to prove they are real and alive. The task can include blinking, smiling, nodding, and so on. However, antispoofing experts observe active detection to be highly vulnerable and generally imperfect.

While fraudsters can learn how to bypass it through reverse-engineering, regular users have to deal with long waiting time and increased customer friction. Therefore, passive approach is generally preferred.

Face liveness detection: Definition

Face liveness detection is the ability of a system to detect and verify that a presented face belongs to a bona fide living person.

Facial liveness encompasses a group of characteristics and traits that are inherent to a living person’s face. In turn, facial liveness detection focuses on spotting and verifying these traits.

These traits generally include:

Anatomical properties. Skin texture and coloring, facial curvature and depth, head contour, etc.
Life signals. Blinking, lip and nose movement, wrinkling, and so on.
Other. Facial expressions, scenic clues, etc.

There are two major types of facial liveness detection in antispoofing: passive and active liveness detection. While the former performs its function in the background, the latter focuses on a challenge-response approach.

Anonymous

Search

Active Facial Liveness Detection

Page actions

Contents