A security testing method and system for Face ID authentication

Abstract

The present invention discloses a security testing method and system for Face ID identity authentication, which belongs to the field of information security technology. The reference scattered image with different depth information generated by the original depth-sensing camera of the device under test is collected; the reference scattered image is preprocessed; according to the preprocessed reference scattered image with different depth information, a "depth information-infrared scattered displacement" mapping relationship is constructed based on the peak signal-to-noise ratio, and a depth mapping modulation function is obtained by polynomial fitting; the target depth image is modulated into the preprocessed reference scattered image with maximum depth information, and the pixel points in the infrared scattered image are reset to a preset size using a point spread function; the infrared scattered image to be tested is projected so that the original depth-sensing camera of the device under test obtains a false target depth image, thereby realizing security testing. The present invention can interfere with the imaging of the original depth-sensing camera, simulate non-existent depth information, and has high test accuracy.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a security testing method and system for Face ID identity authentication. Background Art

[0002] With the advent of the information age, biometric recognition technology has flourished. Facial recognition, as a mainstream method of identity authentication, has been widely used in fields such as smartphones and smart door locks. Face ID is a 3D facial authentication technology that uses a depth camera to capture 3D facial information for identity authentication. Currently, many commercial products use TrueDepth cameras as depth cameras to deploy Face ID. These cameras employ structured light depth imaging technology to capture 3D facial images of users for identity authentication.

[0003] Face ID, based on 3D facial recognition, often has extremely high authentication privileges and can be used for key applications such as phone unlocking and financial payments. Because it uses 3D images, common authentication spoofing methods, such as photo attacks and video playback attacks, are often ineffective against Face ID, ensuring high security for such products. However, a malicious attack on a TrueDepth camera would seriously threaten the victim's privacy and financial security.

[0004] Currently, there are many attack and defense testing methods for two-dimensional face authentication technology, but there are no attack and defense countermeasures for three-dimensional face authentication. Therefore, there is an urgent need for a security testing method for Face ID authentication to explore potential vulnerabilities in the TrueDepth camera and improve the security and reliability of authentication technology. Summary of the Invention

[0005] In response to the above-mentioned problems in the prior art, the present invention provides a security testing method and system for Face ID identity authentication, which can interfere with the structured light imaging module of the original depth-sensing camera to simulate non-existent depth information without relying on the real infrared scattergram of the test object, and has high test accuracy.

[0006] The technical solution of the present invention is:

[0007] In a first aspect, the present invention provides a security testing method for Face ID authentication, comprising the following steps:

[0008] Step 1: Collect infrared scattered images projected by the TrueDepth camera of the device under test onto planes at specified different distances as reference scattered images with different depth information;

[0009] Step 2: preprocessing the reference scattered point image to obtain a preprocessed reference scattered point image with different depth information;

[0010] Step 3: Based on the pre-processed reference scattered point images with different depth information, a "depth information-infrared scattered point displacement" mapping relationship is constructed based on the peak signal-to-noise ratio, and a depth mapping modulation function is obtained by polynomial fitting;

[0011] Step 4: modulate the target depth image into the pre-processed reference scattered image of the maximum depth information, and use the point spread function to reset the pixels in the infrared scattered image to a preset size to obtain the infrared scattered image to be tested;

[0012] Step 5: Project the infrared scattered image to be tested so that the original depth-sensing camera of the device under test can obtain a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, thus achieving security testing.

[0013] Furthermore, the distances between the different distance planes specified in step 1 and the TrueDepth camera of the device under test are 0.5-1 m.

[0014] Furthermore, the preprocessing includes pixel value transformation and filtering.

[0015] Furthermore, the step 2 includes:

[0016] 2.1) Perform piecewise linear transformation on the pixels of the infrared scattered image;

[0017] 2.2) Use a sliding window to traverse all pixels of the transformed infrared scattered image. If the center pixel in the window has the maximum grayscale value of the current window, the grayscale value of the center pixel is retained. Otherwise, the grayscale value of the center pixel in the window is set to 0.

[0018] Furthermore, the step 3 includes:

[0019] 3.1) Take the reference scattered image of the maximum depth information after preprocessing as the original image, intercept the local image I of the original image through the rectangular frame, and use {x center ,y center The ,w,h} quadruple represents the coordinates of the center point and the length and width of the rectangular frame used to intercept the local image I of the original image;

[0020] 3.2) Take any other reference scattered image of depth information as the noise image, intercept the local image K of the noise image through the rectangular frame, and use {x′ center ,y center The ,w,h} quadruple represents the coordinates of the center point and the length and width of the rectangular frame used to intercept the local image K of the noise image;

[0021] 3.3) Traverse x′ on the noise image center , respectively calculate the local image I and different x′ center The peak signal-to-noise ratio between the local images K obtained under the given value is obtained, the local image K_max corresponding to the maximum peak signal-to-noise ratio is obtained, and the pixel distance between the horizontal coordinate of the center point of the rectangular frame of the local image K_max and the horizontal coordinate of the center point of the rectangular frame of the local image I is calculated as the infrared scattered point displacement;

[0022] 3.4) Return to step 3.2), traverse the reference scattered point images of the remaining depth information, obtain the "depth information-infrared scattered point displacement" mapping relationship, and obtain the depth mapping modulation function through polynomial fitting.

[0023] Furthermore, the peak signal-to-noise ratio is calculated as follows:

[0024]

[0025]

[0026] Among them, PSNR represents peak signal-to-noise ratio, MSE represents mean square error, w and h represent the length and width of the local image, MAX I represents the maximum pixel value of the local image I, I(.) represents the local image I, K(.) represents the local image K, and (i, j) represents the pixel coordinates.

[0027] Furthermore, the step 4 includes:

[0028] 4.1) Using the pre-processed reference scatter image of the maximum depth information as the initial template for simulation;

[0029] 4.2) Substitute the depth information of the target depth image into the depth mapping modulation function, calculate the required offset of the pixel center point, and modify the initial template;

[0030] 4.3) Using the point spread function, the pixels in the modified initial template are reset to a preset size.

[0031] In a second aspect, the present invention provides a system for implementing the above-mentioned security testing method for Face ID authentication, comprising:

[0032] An image acquisition module is used to collect infrared scattered images projected by the TrueDepth camera of the device under test onto planes at specified different distances as reference scattered images with different depth information;

[0033] An image processing module is configured to preprocess the reference scattered point image to obtain a preprocessed reference scattered point image with different depth information; construct a "depth information-infrared scattered point displacement" mapping relationship based on the peak signal-to-noise ratio based on the preprocessed reference scattered point image with different depth information, and obtain a depth mapping modulation function through polynomial fitting; modulate the target depth image into the preprocessed reference scattered point image with maximum depth information, and use a point spread function to reset the pixels in the infrared scattered point image to a preset size to obtain an infrared scattered point image to be tested;

[0034] The dot matrix projection module is used to project the infrared scattered image to be tested, so that the original depth sensing camera of the device under test can obtain a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, thus achieving security testing.

[0035] Furthermore, the device under test is equipped with a TrueDepth camera and has a Face ID authentication function.

[0036] The beneficial effects of the present invention are:

[0037] (1) By extracting the scattered points of infrared structured light based on the original depth camera, the present invention can effectively extract the center position of the projection point, remove background and noise, and achieve filtering. Compared with the relationship between the displacement of the infrared dot pattern obtained by directly calculating the depth information, the accuracy of the mapping function can be significantly improved.

[0038] (2) The present invention utilizes the depth information of the object and the mapping relationship between the calculated depth and the scatter point position to generate an infrared scatter point image for testing, simulating the real infrared scatter point image of the object. The projection image has a very high similarity with the dot matrix image that the original depth-sensing camera should have received, without relying on the real infrared scatter point image of the test object. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a diagram of the security testing system architecture for Face ID authentication proposed by the present invention;

[0040] Figure 2 This is a flowchart of a security testing method for Face ID authentication highlighted in the present invention;

[0041] Figure 3 Schematic diagram of the method for obtaining reference scatter plots of different distance planes proposed by the present invention;

[0042] Figure 4 Schematic diagram of the PSNR calculation method proposed in the present invention;

[0043] Figure 5This is a schematic diagram of the simulated scatter plot projection method proposed in the present invention. DETAILED DESCRIPTION

[0044] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0045] The accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0046] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all steps. For example, some steps may be decomposed, while some steps may be combined or partially combined, so the actual execution order may change according to actual circumstances.

[0047] The present invention provides a security testing system for Face ID identity authentication. Figure 1 The system architecture diagram of the exemplary embodiment is shown in FIG. Figure 1 As shown, the system architecture includes an image acquisition module, an image processing module, a dot projection module, and a device under test with a TrueDepth camera. The TrueDepth camera includes an infrared scattered point projection module and a depth generation module. The device under test has Face ID authentication.

[0048] Among them, the infrared scattered point projection module in the original depth camera can emit 30,000 points arranged in a fixed pattern.

[0049] The depth generation module in the TrueDepth camera is a mathematical model created by the neural network or image matching of the TrueDepth camera and its associated devices (including but not limited to iPhone, iPad, etc.).

[0050] The image acquisition module is used to collect the infrared scattered image emitted by the infrared scattered projection module. It can be a device capable of receiving and imaging infrared light with a wavelength of 780nm to 2526nm, including but not limited to mobile phones, cameras or night vision devices without infrared filters.

[0051] The image processing module is another terminal connected to the image acquisition module and the dot matrix projection module, and can be a background server that provides image analysis and processing. The dot matrix projection module is an infrared light source with programmable infrared dot matrix projection capability.

[0052] The image acquisition module and the dot matrix projection module communicate with the image processing module respectively through wired or wireless means. The image acquisition module transmits the collected infrared scattered point image to the image processing module through wired or wireless means, and the processed infrared scattered point image can be transmitted to the dot matrix projection module for projection.

[0053] In one embodiment, a mobile phone equipped with a TrueDepth camera was used as the tested device. The TrueDepth camera's infrared scattered-dot projection module emitted 30,000 dots arranged in a fixed pattern. The image acquisition module, comprised of an infrared camera, was used to capture the 940nm infrared scattered-dot image emitted by the infrared scattered-dot projection module.

[0054] The image processing module receives the infrared scattered point image and performs preprocessing. It obtains the mapping relationship between depth and scattered point position by calculating the peak signal-to-noise ratio of the processed infrared scattered point image. According to the mapping relationship, the target depth image is mapped to the infrared scattered point image to be tested.

[0055] The dot projection module receives the infrared scattered image to be tested and projects it, allowing the TrueDepth camera in the tested device to obtain the infrared scattered image to be tested and generate a target depth image, thereby testing the model used for Face ID authentication in the test device.

[0056] The following is an explanation of the security testing method based on the TrueDepth camera of this exemplary embodiment. The application scenarios of this method include but are not limited to: the user first obtains the infrared scattered point image projected by the TrueDepth camera at different depths as the reference scattered point image, then filters the reference scattered point image to obtain the pre-processed infrared scattered point image; and uses the peak signal-to-noise ratio to construct the "depth information-infrared scattered point displacement" mapping relationship, and obtains the depth mapping modulation function through polynomial fitting; then uses the fitted depth mapping modulation function to arrange the scattered points, modulates the target depth image into the reference scattered point image, and uses the point spread function to reset the infrared scattered points to a suitable size. The target depth image can be a face, a plane, etc.; finally, uses the dot matrix projection module to project the designed infrared scattered point image to be tested, so that the depth generation module in the TrueDepth camera obtains a false target depth image, completing the security test of the TrueDepth camera.

[0057] Figure 2 An exemplary process of a security testing method for Face ID authentication is shown, including:

[0058] Step 1: The image acquisition module collects infrared scattered images projected by the TrueDepth camera of the device under test onto planes at specified distances (the distances serve as depth information) as reference scattered images and transmits them to the image processing module;

[0059] Step 2: The image processing module preprocesses the reference scattered-point image to obtain a preprocessed reference scattered-point image. In this embodiment, the preprocessing includes pixel value transformation, filtering, etc.

[0060] Step 3: Based on the pre-processed reference scattered point image, a "depth information-infrared scattered point displacement" mapping relationship is constructed based on the peak signal-to-noise ratio, and a depth mapping modulation function is obtained by polynomial fitting;

[0061] Step 4: modulate the target depth image into the preprocessed reference scattered image, and use the point spread function to reset the infrared scattered image to a suitable size to obtain the infrared scattered image to be tested;

[0062] In step 5, the dot projection module projects the designed infrared scattered image to be tested, so that the depth generation module in the TrueDepth camera obtains a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, completing the security test of the TrueDepth camera.

[0063] The following is a detailed description of each of the above steps.

[0064] In step 1, if Figure 3 As shown, a reflective plate is placed 1 meter in front of the TrueDepth camera to cover the shooting angle of the TrueDepth camera. At the same time, an infrared camera is placed above the receiving lens of the TrueDepth camera as an image acquisition module. After observing the infrared scattered image on the display of the infrared camera, the infrared scatter image on the current distance plane is obtained. Similarly, reflective plates are placed every 5 cm between 60 cm and 95 cm to obtain infrared scattered image on each distance plane. The above images are used as reference scattered images and transmitted to the image processing module for subsequent calculation of the mapping relationship between depth information and infrared scattered point displacement.

[0065] In step 2, since the infrared scattered point images obtained at different depths contain a large amount of noise, directly calculating the mapping relationship between depth information and infrared scattered point displacement will result in large errors. This noise mainly includes infrared light reflected from the target object itself, infrared light reflected from the target object's surrounding environment, noise generated by the infrared camera when shooting at low brightness, and noise caused by the infrared camera's resolution limitations.

[0066] Taking into account the characteristic that the scattered points projected by the infrared scattered point projection module in the TrueDepth camera must be the brightest points in a certain area in the surrounding area in order to be captured and recognized as depth information by the depth camera, this paper proposes to filter the infrared scattered points of the replayed target using a high-pass filtering algorithm. The specific method is as follows:

[0067] 1) Improve the contrast of image details.

[0068] Perform piecewise linear transformation on the infrared scattered point image to amplify the pixel grayscale value difference and make the details in the image clearer. In this embodiment, the grayscale of the image is divided into three parts, and then different linear transformations are performed on the pixel values ​​of each part. The principle of pixel value transformation is:

[0069]

[0070] Among them, O(x,y) represents the pixel value of the pixel point (x,y) after transformation, a1, a2, and a3 represent transformation coefficients, b1, b2, and b3 represent transformation constants, I(x,y) represents the pixel value of the pixel point (x,y) before transformation, and H1 and H2 represent segmentation thresholds.

[0071] 2) Using a sliding window method to traverse all pixel points of the transformed infrared scattered point image, filtering is performed from left to right and from top to bottom to obtain a filtered infrared scattered point image, which is clearer.

[0072] Generally speaking, each infrared scattered point in an infrared scattered point image is sparsely distributed across the image. That is, within a small window, there is only one brightest point, which serves as the scatter point to be extracted. If the center pixel within the window has the maximum grayscale value, the grayscale value of the center pixel is retained. Otherwise, the grayscale value of the center pixel is set to 0. After traversing all pixels in the transformed infrared scattered point image, the center point of each infrared scattered point can be extracted.

[0073] In this embodiment, a local high-pass filter is used for filtering, and a calculation process is performed using a small window range as the calculation unit. For example, a 5×5 area is used as the window for a single calculation process. Alternatively, a window of different sizes can be determined based on the pixel range occupied by the scattered points. If the maximum grayscale value is located at the midpoint of the window, that is, the maximum grayscale value is at the center of the window, then that point is recorded as an infrared scattered point, and its grayscale value is retained.

[0074] In step 3, the peak signal-to-noise ratio is used to calculate the mapping relationship between the depth information and the infrared scattered point displacement.

[0075] The peak signal-to-noise ratio (PSNR) is one of the indicators for measuring image quality. PSNR is defined based on MSE (mean square error). Given an original image I corresponding to a window of size m*n and a noise image K after adding noise to it, MSE can be defined as:

[0076]

[0077] PSNR can be defined as:

[0078]

[0079] Among them MAX I The unit of PSNR is dB. If each pixel is represented by 8 bits of binary, its value is 2^8-1=255. The larger the PSNR value, the better the image quality. Generally speaking, the relationship between PSNR and image quality is:

[0080] Above 40dB Excellent image quality (very close to the original) 30-40dB Good image quality (slightly distorted but acceptable) 20-30dB Poor image quality Less than 20dB Unacceptable image quality

[0081] The scatter points projected by the infrared scattered point projection module in the TrueDepth camera are determined by the diffractive optical element, and the scatter points projected by the infrared scattered point projection module within the same TrueDepth camera are fixed. The imaging principle of the TrueDepth camera uses the offset of the scattered points to calculate depth. This scatter point offset only occurs horizontally, not vertically. Therefore, at the same height in the filtered infrared scattered point image, the displacement between pixels represents the corresponding depth change.

[0082] like Figure 4 As shown, taking the infrared scattered point pattern at 95cm as an example, the local image I of the pre-processed infrared scattered point image at a distance of 1m is intercepted through a rectangular window, and {x center ,y center , w, h} quadruple represents the center coordinates and length and width of the rectangular box. At the same horizontal height of the 95cm image, traverse the same size intercepted image K from left to right, and use {x′ center ,y center The quadruple {,w,h} represents the coordinates of the center point and the length and width of the rectangular box. The peak signal-to-noise ratio between image K and image I is calculated. The maximum PSNR corresponds to the horizontal coordinate x″ of the center point of the rectangular box of image K. center The horizontal coordinate x of the center point of the rectangular frame of image I center There is a mapping relationship between the pixel distance change between the two images and the depth difference between the two images.

[0083] Repeat the above steps, intercept image K from other images between 60cm and 95cm, calculate the pixel distance changes respectively, and use function interpolation to obtain the "depth information-infrared scattered point displacement" mapping relationship. After polynomial fitting, the depth mapping modulation function can be obtained.

[0084] In step 4, the infrared scattered image that the TrueDepth camera should have received is simulated based on the depth information of the target depth image. The specific steps are as follows:

[0085] 1) The preprocessed reference scatter image with maximum depth information is used as the initial template for simulation.

[0086] 2) Substitute the depth information of the target depth image into the depth mapping modulation function obtained in step 3, calculate the required offset of the pixel center point, and modify the initial template. However, the resulting dot matrix only contains the target dot matrix pixel center point, which does not meet the size requirements for projection.

[0087] 3) Use the point spread function to resize the modified initial template to the appropriate size. The point spread function is the distribution function of the diffraction spot formed by a point light source after passing through the optical system. It characterizes the characteristics of the optical system in the spatial domain. Geometric optics analysis shows that the point spread function of image degradation caused by optical system defocus is a uniformly distributed circular (or square) spot. This point spread function can be expressed as:

[0088]

[0089] Where h(.) represents the point spread function, (x, y) represents the pixel coordinates before diffusion, and R is the radius of the defocused spot. For the infrared dot matrix emitted by the same camera, the radius R of each point captured in the camera should be the same. Thus, the rearranged simulated infrared dot matrix is ​​obtained as the infrared scattered point image to be tested.

[0090] In step 5, the above method can be used to obtain a simulated real infrared scattered image, such as Figure 5 As shown, this example uses an infrared scattered-point projector and a projection reflector to project the infrared scattered-point image to be tested, so that the depth generation module in the TrueDepth camera obtains a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, completing the security test of the TrueDepth camera.

[0091] Specifically, first turn off the infrared scatter projection module in the original depth camera, such as using a narrow-band filter to block the light it emits, so that it cannot project the infrared scatter image normally, and then place an infrared scatter projector above the lens of the infrared scatter projection module. The simulated infrared scatter image to be tested is transmitted from the data processing module to the infrared scatter projector through the communication interface. A projection reflector is placed 1 meter in front of the infrared scatter projector. The infrared scatter image to be tested is reflected to the original depth camera of the device under test through the projection reflector. When the infrared lens of the original depth camera receives the scatter map, it will perform depth calculation in combination with the mathematical model created by the built-in neural network, that is, the target depth image submitted is recognized by the depth camera and can be used for subsequent Face ID authentication tasks to complete the security test.

[0092] It should be noted that although the image acquisition and processing and depth generation modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0093] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented as the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system". Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and implementation are intended to be exemplary only, and the true scope and spirit of the present invention are indicated by the claims.

[0094] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings and that various modifications and variations can be made without departing from the scope thereof, which is limited only by the appended claims.

Claims

1. A security testing method for Face ID authentication, characterized in that: The following steps are involved: Step 1: Collect infrared scattered images projected by the TrueDepth camera of the device under test onto specified planes at different distances as reference scattered images with different depth information; Step 2: preprocessing the reference scattered point image to obtain a preprocessed reference scattered point image with different depth information; Step 3: Based on the pre-processed reference scattered point images with different depth information, a "depth information-infrared scattered point displacement" mapping relationship is constructed based on the peak signal-to-noise ratio, and a depth mapping modulation function is obtained through polynomial fitting; The step 3 includes: 3.1) Take the reference scattered image of the maximum depth information after preprocessing as the original image, intercept the local image I of the original image through the rectangular frame, and use {x center ,y center The ,w,h} quadruple represents the coordinates of the center point and the length and width of the rectangular frame used to intercept the local image I of the original image; 3.2) Take any other reference scattered image of depth information as the noise image, intercept the local image K of the noise image through the rectangular frame, and use {x′ center ,y center The ,w,h} quadruple represents the coordinates of the center point and the length and width of the rectangular frame used to intercept the local image K of the noise image; 3.3) Traverse x′ on the noise image center , respectively calculate the local image I and different x′ center The peak signal-to-noise ratio between the local images K obtained under the given value is obtained, the local image K_max corresponding to the maximum peak signal-to-noise ratio is obtained, and the pixel distance between the horizontal coordinate of the center point of the rectangular frame of the local image K_max and the horizontal coordinate of the center point of the rectangular frame of the local image I is calculated as the infrared scattered point displacement; 3.4) Return to step 3.2) and traverse the reference scattered point images of the remaining depth information to obtain the "depth information-infrared scattered point displacement" mapping relationship, and obtain the depth mapping modulation function through polynomial fitting; Step 4: modulate the target depth image into the pre-processed reference scattered image of the maximum depth information, and use the point spread function to reset the pixels in the infrared scattered image to a preset size to obtain the infrared scattered image to be tested; In step 5, the infrared scattered image to be tested is projected so that the original depth-sensing camera of the device under test obtains a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, thus achieving security testing.

2. A security testing method for Face ID authentication according to claim 1, characterized in that: The distance between the different distance planes specified in step 1 and the TrueDepth camera of the device under test is 0.5-1m.

3. A security testing method for Face ID authentication according to claim 1, characterized in that: The preprocessing includes pixel value transformation and filtering.

4. A security testing method for Face ID authentication according to claim 1, characterized in that: The step 2 includes: 2.1) Perform piecewise linear transformation on the pixels of the infrared scattered image. The pixel value transformation formula is: Where O(x,y) represents the pixel value of the pixel point (x,y) after transformation, a1, a2, a3 represent transformation coefficients, b1, b2, b3 represent transformation constants, I(x,y) represents the pixel value of the pixel point (x,y) before transformation, H1, H2 represent segmentation thresholds; 2.2) Use a sliding window to traverse all pixels of the transformed infrared scattered image. If the center pixel in the window has the maximum grayscale value of the current window, the grayscale value of the center pixel is retained. Otherwise, the grayscale value of the center pixel in the window is set to 0.

5. A security testing method for Face ID authentication according to claim 1, characterized in that: The calculation formula of the peak signal-to-noise ratio is: Among them, PSNR represents peak signal-to-noise ratio, MSE represents mean square error, w and h represent the length and width of the local image, MAX I Represents the maximum pixel value of local image I, I(.) represents local image I, K(.) represents local image K, and (i, j) represents the pixel coordinates.

6. A security testing method for Face ID authentication according to claim 1, characterized in that: The step 4 includes: 4.1) Using the pre-processed reference scatter image of the maximum depth information as the initial template for simulation; 4.2) Substitute the depth information of the target depth image into the depth mapping modulation function, calculate the required offset of the pixel center point, and modify the initial template; 4.3) Using the point spread function, the pixels in the modified initial template are reset to a preset size.

7. A security testing method for Face ID authentication according to claim 1, characterized in that: The calculation formula of the point spread function is: Where h(.) represents the point spread function, (x, y) represents the pixel coordinates before diffusion, and R is the radius of the defocused spot.

8. A system for implementing the security testing method for Face ID authentication according to claim 1, characterized in that: include: An image acquisition module is used to collect infrared scattered images projected by the TrueDepth camera of the device under test onto planes at specified different distances as reference scattered images with different depth information; An image processing module is configured to preprocess the reference scattered point image to obtain a preprocessed reference scattered point image with different depth information; construct a "depth information-infrared scattered point displacement" mapping relationship based on the peak signal-to-noise ratio based on the preprocessed reference scattered point image with different depth information, and obtain a depth mapping modulation function through polynomial fitting; modulate the target depth image onto the preprocessed reference scattered point image with maximum depth information, and use a point spread function to reset the pixels in the infrared scattered point image to a preset size to obtain an infrared scattered point image to be tested; The dot matrix projection module is used to project the infrared scattered image to be tested, so that the original depth sensing camera of the device under test can obtain a false target depth image. If the device under test is unlocked successfully, the device under test is unsafe; otherwise, the device under test is safe, thus achieving security testing.

9. The system according to claim 8, characterized in that The device under test is equipped with a TrueDepth camera and has a Face ID authentication function.

Images