An anti-cracking method and system for slider verification codes

Abstract

The present invention discloses an anti-cracking method for slider verification codes. This method adds steps of automatically detecting the click position of the slider, simulating human sliding, and sliding with random numbers to the original verification code process, so that machines cannot identify and decrypt through automatic calculation.

Description

Technical Field

[0001] The present invention relates to an anti-cracking technology in the field of CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart). Background Art

[0002] The Completely Automated Public Turing test to tell Computers and Humans Apart (abbreviated as CAPTCHA), commonly known as the verification code, is a public automated program that distinguishes whether a user is a computer or a human, preventing users from using program automata for automatic submission injection and avoiding unnecessary attacks on server interaction processing. The main purpose of the verification code is to enforce human-computer interaction to resist machine automation attacks. In order to ensure the stability of the server system and the security of user information, the verification code technology is adopted by the vast majority of website platforms.

[0003] The slider verification code is a commonly used verification code at present. Its essence is to slide the slider to the correct position and submit it for verification on the app or website. Only after passing the verification can a certain function be used. It is often used in functions such as user login, voting, and user evaluation and suggestion. For enterprises, it has high security, prevents the interface from being brushed, and reduces the server pressure. For users, the interface is comfortable and beautiful, bringing a more interesting verification process to users and enhancing the user interaction experience. In addition, some websites also implant advertisements in the verification background pictures, bringing certain publicity effects and economic benefits.

[0004] However, with the development of machine automatic recognition technology nowadays, it is becoming easier and easier for machines to crack the slider verification code, and the accuracy rate is also getting higher and higher. The recognition steps are generally divided into acquisition - calculation - cracking. The acquisition step is generally to find the verification code picture and the slider notch picture. According to the picture download address, the original picture can be obtained, and then the binary code of the original picture is downloaded by simulating the browser request and written into a file to save the picture.

[0005] In order to crack the verification code, it is necessary to calculate the sliding distance of the slider. The steps generally use means such as grayscale processing, matching, and scaling ratio calculation.

[0006] Grayscale processing: Perform grayscale processing on the verification code picture. Since the grayscale values are different, the slider notch and the background picture can be distinguished.

[0007] Matching: Based on the RGB code of the slider notch and the background picture after grayscale processing, the position of the slider notch in the background picture can be matched and obtained.

[0008] Scaling ratio calculation: Compare the size of the verification code picture on the actual web page with the downloaded original picture to obtain the scaling ratio, so as to calculate the precise distance that the slider actually slides.

[0009] Finally, use technologies such as selenium to hold the slider element, and slide to the corresponding position according to the sliding distance calculated by the sliding, and the cracking is successful.

[0010] Therefore, even if the difficulty is increased by randomly replacing the verification code image or adjusting the position of the slider notch, as long as a more optimized algorithm is used, it is still possible for machines to recognize and crack the verification code, making it impossible to distinguish between machines and humans, and the slider verification code itself loses its meaning.

[0011] Therefore, methods and systems are needed that can improve the deficiencies in the prior art. Summary of the Invention

[0012] This Summary of the Invention is provided to introduce in a simplified form some concepts that will be further described in the Detailed Description section below. This Summary of the Invention is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to help determine the scope of the claimed subject matter.

[0013] Through the analysis of machine automatic recognition and cracking, it is found that there are differences in the click position of the slider dragged by the machine and that of a normal person, as well as the speed changes during the process of the machine dragging the slider and that of a normal person dragging the slider. Therefore, the present invention can extract the slider movement characteristics based on this to find corresponding anti-cracking methods, ultimately achieving the purpose of strengthening the verification code.

[0014] In the present invention, the verification code unlocking is detected in two rounds:

[0015] In the first round of detection, the click position coordinates of the slider are obtained, recorded, and data analysis is performed. Whether it is machine recognition is judged based on whether the position coordinates are fixed.

[0016] In the second round of detection, the instantaneous acceleration of the slider in the slider verification code is calculated in advance and automatically stored in a data list in the form of key-value pairs. Any slicing operation can be performed on the list according to the length of the returned list. If the machine slides the slider at a constant speed, it is judged based on whether the acceleration is 0; if the machine slides to simulate the sliding of a relatively real person, it is judged based on whether the instantaneous accelerations during the dragging process are equal; if the machine slides using a random number hash slide, the initial acceleration set and the end acceleration set are obtained for comparison, and the user's sliding characteristics are combined for judgment.

[0017] Specifically, in an embodiment of the present invention, an anti-cracking method for a slider verification code is provided, and the method includes:

[0018] Obtain the position coordinates of the slider click and generate a playback video of the slider sliding;

[0019] Determine that the slider click is made by a machine when the number of times the position coordinates are the same reaches a threshold number of times;

[0020] Decompose the playback video and perform picture cutting;

[0021] Process the cut images to determine the position of the slider in the cut images and calculate the pixel spacing between the sliders in each cut image based on the position;

[0022] Determine the time interval of each cut image according to the duration and number of frames of the playback video;

[0023] Determine the sliding speed of the slider between each cut image based on the time interval and the pixel spacing, and determine the instantaneous acceleration of the slider between each frame based on the sliding speed;

[0024] Determine that the slider is slid by the machine when the number of times the instantaneous accelerations are equal reaches a threshold number of times; and

[0025] When the number of times the instantaneous accelerations are equal does not reach the threshold number of times, determine whether the slider is slid by the machine based on the initial acceleration set and the final acceleration set of the slider.

[0026] In an embodiment of the present invention, the position coordinates are obtained within a predetermined time period of the playback video, and when it is determined that the slider click is made by the machine, the position coordinates or the IP address of the logged-in machine are stored in the database.

[0027] In an embodiment of the present invention, the method further includes excluding abnormal situations from the playback video.

[0028] In an embodiment of the present invention, processing the cut images includes reading the RGB encoding of the cut images and performing grayscale processing on the cut images according to the RGB codes, and the cut images are cut frame by frame.

[0029] In this embodiment of the present invention, the reading of the RGB encoding and the grayscale processing are multi-threaded.

[0030] In an embodiment of the present invention, the instantaneous acceleration is output in the form of key-value pairs and automatically saved to a list for slicing operation on the data in the list.

[0031] In this embodiment of the present invention, the initial acceleration set and the final acceleration set are obtained by slicing the list, and each instantaneous acceleration in the initial acceleration set and the final acceleration set is compared one by one to determine whether the slider is slid by the machine.

[0032] In an embodiment of the present invention, the situation where the number of times the instantaneous accelerations are equal reaches the threshold number of times includes the situation where the instantaneous acceleration is zero.

[0033] In one embodiment of the present invention, a system for preventing cracking of slider verification codes is provided. The system includes:

[0034] An input information acquisition module configured to obtain the position coordinates of slider clicks and generate a playback video of slider sliding;

[0035] A slider click position detection module configured to determine that the slider click is made by a machine when the number of times the position coordinates are the same reaches a threshold number of times;

[0036] An image processing module configured to:

[0037] Decompose the playback video and perform image cutting;

[0038] Process the cut images to determine the position of the slider in the cut images;

[0039] A slider acceleration calculation module configured to:

[0040] Calculate the pixel spacing between the sliders in each cut image based on the position;

[0041] Determine the time interval of each cut image according to the duration and number of frames of the playback video; and

[0042] Determine the sliding speed of the slider between each cut image based on the time interval and the pixel spacing and determine the instantaneous acceleration of the slider between each frame based on the sliding speed;

[0043] A machine sliding detection module configured to:

[0044] Determine that the slider sliding is made by a machine when the number of times the instantaneous accelerations are equal reaches a threshold number of times;

[0045] When the number of times the instantaneous accelerations are equal does not reach the threshold number of times, determine whether the slider sliding is made by a machine based on the initial acceleration set and the final acceleration set of the slider.

[0046] In yet another embodiment of the present invention, a computer-readable medium storing computer-executable instructions is provided. These instructions include:

[0047] Instructions for obtaining the position coordinates of slider clicks and generating a playback video of slider sliding;

[0048] Instructions for determining that the slider click is made by a machine when the number of times the position coordinates are the same reaches a threshold number of times;

[0049] Instructions for decomposing the playback video and performing picture cutting;

[0050] Instructions for processing the cut pictures to determine the position of the slider in the cut pictures and calculating the pixel spacing between the slider in each cut picture based on the position;

[0051] Instructions for determining the time interval of each cut picture according to the duration and number of frames of the playback video;

[0052] Instructions for determining the sliding speed of the slider between each cut picture based on the time interval and the pixel spacing and determining the instantaneous acceleration of the slider between each frame based on the sliding speed;

[0053] Instructions for determining that the slider is slid by a machine when the number of times the instantaneous acceleration is equal reaches a threshold number; and

[0054] Instructions for determining whether the slider is slid by a machine based on the initial acceleration set and the final acceleration set of the slider when the number of times the instantaneous acceleration is equal does not reach the threshold number.

[0055] After studying the following description of specific exemplary embodiments of the present invention in conjunction with the accompanying drawings, other aspects, features, and embodiments of the present invention will be apparent to those of ordinary skill in the art. Although the features of the present invention may be discussed below with respect to certain embodiments and drawings, all embodiments of the present invention may include one or more of the advantageous features discussed herein. In other words, although one or more embodiments may be discussed as having certain advantageous features, one or more of such features may also be used in accordance with the various embodiments of the present invention discussed herein. In a similar manner, although the exemplary embodiments may be discussed below as device, system, or method embodiments, it should be understood that such exemplary embodiments may be implemented in various devices, systems, and methods. Brief Description of the Drawings

[0056] In order to understand in detail the manner in which the above-described features of the present disclosure are used, the above briefly summarized content may be described in more detail with reference to the various aspects, some of which are illustrated in the drawings. It should be noted, however, that the drawings only illustrate certain typical aspects of the present disclosure and should not be considered to limit its scope, as the description may admit of other equally effective aspects.

[0057] Figure 1 It is a schematic diagram of the overall architecture of an anti-cracking system for slider verification codes according to an embodiment of the present disclosure.

[0058] Figure 2Shows the overall flowchart of an anti-cracking system for slider verification codes according to an embodiment of the present disclosure.

[0059] Figure 3 Shows a graph of the sliding speed relative to the sliding distance in a sliding operation according to an embodiment of the present disclosure.

[0060] Figure 4 Shows the flowchart of an anti-cracking method for slider verification codes according to an embodiment of the present disclosure.

[0061] Figure 5 Shows the block diagram of an anti-cracking system for slider verification codes according to an embodiment of the present disclosure. Detailed Description of the Invention

[0062] The following will describe each embodiment in more detail with reference to the accompanying drawings that form a part of the present invention and illustrate various specific exemplary embodiments. However, each embodiment can be implemented in many different forms and should not be construed as limiting the embodiments set forth herein; rather, these embodiments are provided so that the present disclosure will be thorough and complete, and the scope of these embodiments will be fully conveyed to those of ordinary skill in the art. Each embodiment can be implemented as a method, system, or device. Therefore, these embodiments can take the form of a hardware implementation, a full software implementation, or an implementation combining software and hardware aspects. Therefore, the following detailed description is not limiting.

[0063] The steps in each flowchart can be executed by hardware (e.g., processors, engines, memories, circuits), software (e.g., operating systems, applications, drivers, machine / processor executable instructions), or a combination thereof. As those of ordinary skill in the art will understand, the methods involved in each embodiment may include more or fewer steps than those shown.

[0064] In view of the current situation that it is becoming increasingly easy for machines to automatically recognize slider verification codes and the accuracy is getting higher and higher, the present invention utilizes the characteristics that machines can only calculate the sliding distance but cannot simultaneously simulate the slider click position and accurately simulate the slider movement speed, and mines security reinforcement means from the cracking steps to prevent machines from recognizing verification codes, thereby achieving the purposes of preventing malicious logins, brute-force cracking, etc., and maintaining the security of the website platform, the normal operation of product functions, and the security of user information.

[0065] The following will describe various aspects of the present disclosure in detail through block diagrams, data flow diagrams, and method flowcharts.

[0066] Figure 1 Is a schematic diagram of the overall architecture of an anti-cracking system for slider verification codes according to an embodiment of the present disclosure.

[0067] The technical solution of the present invention includes two rounds of detection. In the first round of detection, by obtaining the click position coordinates of the slider ( Figure 1 the initial dragging position of the slider obtained in

[0068] ), recording and performing data analysis, and then in the machine recognition judgment, it is determined whether it is machine recognition according to whether the position coordinates are fixed. In an embodiment of the present invention, the click position is obtained within a predetermined time period, such as 1 second, 2 seconds, etc. The predetermined time period can be any suitable time period and is set by those skilled in the art according to actual needs. Figure 1 In the second round of detection, by analyzing the playback video of the slider sliding to calculate the instantaneous acceleration of the slider in the slider verification code, it is automatically stored in the data list in the form of key-value pairs, and any slicing operation can be performed on the list according to the length of the returned list (

[0069] the calculation of sliding the slider in

[0070] ). In the subsequent machine recognition judgment:

[0071] If the slider slides at a uniform speed, that is, the acceleration is 0, it is determined that the verification code is recognized by the machine;

[0072] Figure 2 If the machine sliding simulates a relatively real human sliding, it is judged according to whether the instantaneous accelerations during the dragging process are equal. Specifically, it can be judged according to whether the number of times of equal instantaneous acceleration reaches the threshold number. The threshold number is not limited to any specific number but can be any suitable number, which can be set by those skilled in the art according to needs;

[0073] If the machine sliding uses random number hashing sliding, the initial acceleration set and the end acceleration set are obtained for comparison, and combined with the user sliding characteristics for judgment.

[0074] The slider click position detection module can also be configured to generate a playback video of the slider sliding. In an embodiment of the present invention, the playback video can be generated in real time through the user input behavior screen recording and playback technology in the big data software field. As those skilled in the art can understand, in other embodiments of the present invention, any suitable other technology can be used to generate the playback video without departing from the scope of the present invention, and the present invention is not limited to any specific playback video generation technology.

[0075] In another embodiment of the present invention, optionally, abnormal processing is also performed on the generated playback video and abnormal situations (if any, such as video stuttering, etc.) are captured. If there is no abnormal situation, the playback video without abnormality is provided to the subsequent module.

[0076] The image processing module receives the playback video and is configured to decompose the playback video, perform frame-by-frame image cutting, and process the cut images. In an embodiment of the present invention, each frame of the obtained image is cut, the RGB encoding of the cut image is read, and the image can be grayscale processed according to the image RGB code. Then, the specific position of the slider in the cut image can be obtained according to the RGB encoding of the slider and the grayscale value of the background image. As those skilled in the art can understand, in other embodiments of the present invention, any suitable other image recognition technology can be used to determine the position of the slider in the image without departing from the scope of the present invention, and the present invention is not limited to any specific image recognition technology.

[0077] Subsequently, the slider acceleration calculation module (not shown for simplicity) can calculate the pixel spacing (pixel difference) between the sliders in each cut image based on the position of the slider in the image. The slider acceleration calculation module is further configured to determine the time interval of each cut image according to the duration and number of frames of the playback video, and determine the sliding speed of the slider between each cut image based on the time interval and the above pixel spacing, and determine the instantaneous acceleration of the slider between each frame based on the sliding speed.

[0078] In an embodiment of the present invention, by way of example and not limitation, if the slider sliding video is 1 second and the video is decomposed into 60 frames, then the interval of each frame of the image is calculated to be 1 / 60 second. In this embodiment, the pixel difference between the sliders in the first frame and the second frame can be, for example, s1, and the pixel difference between the sliders in the second frame and the third frame is s2. It can be obtained that the sliding speed v1 of the slider between the first frame and the second frame of the image is 60s1, and the sliding speed v2 of the slider between the second frame and the third frame of the image is 60s2. Thus, the instantaneous acceleration of the slider sliding is calculated to be a1 = 60(v2 - v1), and so on to obtain all the accelerations. The output results are saved in a list in the form of key-value pairs.

[0079] In another embodiment of the present invention, the above-mentioned image processing and speed / acceleration calculation can be completed via a multi-threaded module (not shown) to achieve higher calculation speed and resource utilization.

[0080] Then, the machine sliding detection module obtains the calculated instantaneous acceleration data of the slider between each frame. In one embodiment of the present invention, machine sliding may simulate real human sliding operations. Specifically, Figure 3 A graph showing the sliding speed versus the sliding distance in a sliding operation according to an embodiment of the present disclosure is shown. As Figure 3 shown by the curve in, since the speed of a human dragging the slider is first fast and then slow as the sliding distance increases. When the specified distance is not reached, the acceleration is positive, and when the last specified distance is reached, the acceleration becomes negative (by way of example and not limitation, when the distance is less than 4 / 5, the acceleration is 1, and when the last 1 / 5 distance is reached, the acceleration becomes -2). However, since the acceleration of a human dragging the slider is non-linear or irregular, it can be judged according to whether the instantaneous accelerations during the dragging process are equal. Accordingly, the machine sliding detection module can detect the simulated human sliding, that is, determine that the slider sliding is made by the machine when the number of times of equal instantaneous accelerations reaches a threshold number. As can be understood by those skilled in the art, the threshold number is not limited to any specific threshold, but can be set by those skilled in the art to any appropriate threshold number according to needs.

[0081] In another embodiment of the present invention, the situation where the number of times of equal instantaneous accelerations reaches the threshold number includes the case of dragging the slider at a normal uniform speed, that is, it can be judged by calculating whether the dragging acceleration is 0. If it is 0, it is judged as machine recognition.

[0082] For the situation where the number of times of equal instantaneous accelerations does not reach the threshold number, the machine may use random number hashing to deceive the detection via dynamic remaining random number sliding, so the sliding acceleration is constantly changing irregularly. However, since a human needs to slowly align the slider notch when dragging the slider, it is first fast and then slow. Accordingly, the machine sliding detection module judges whether the slider sliding is made by the machine based on the initial segment acceleration set and the end segment acceleration set of the slider. Specifically, the machine sliding detection module performs a slicing operation on the list storing the calculated acceleration values, takes the initial segment acceleration set (a1, a2...) with indexes 1, 2... in the list as the initial acceleration, and takes the end segment acceleration set (...a(n - 1), an) with indexes...n - 1, n in the list as the end acceleration, and analyzes the initial acceleration and the end acceleration through point-to-point comparison, that is, compares the first acceleration a1 in the initial segment acceleration set with the first acceleration a(n - m) in the end segment acceleration set, and so on to judge whether it is machine sliding.

[0083] As can be understood by those skilled in the art, in addition to the above calculation method, any other suitable calculation method can be used to determine whether the slider is sliding made by the machine based on the initial acceleration set and the final acceleration set of the slider. The present invention is not limited to any specific calculation method. The number of acceleration values in the acceleration set can also be set by those skilled in the art according to needs to any suitable number, rather than being limited to any specific number.

[0084] Finally, when it is determined that the machine is sliding, data such as the logged-in IP address is automatically saved or recorded in the database for convenient tracking and processing later.

[0085] Figure 4 The flowchart of the anti-cracking method 400 for slider verification codes according to an embodiment of the present disclosure is shown.

[0086] Method 400 starts at step 402. At step 402, the position coordinates of the slider click are obtained and a playback video of the slider sliding is generated. In an embodiment of the present invention, the position coordinates and the playback video are obtained within a predetermined time period.

[0087] At step 404, it is determined that the slider click is made by the machine when the number of times the position coordinates are the same reaches the threshold number of times. In an embodiment of the present invention, when it is determined that the slider click is made by the machine, the position coordinates of the slider click or the IP address of the logged-in machine are stored in the database.

[0088] At step 406, the playback video is decomposed and picture cutting is performed. In an embodiment of the present invention, before decomposition, the method further includes excluding abnormal situations from the playback video.

[0089] At step 408, the cut pictures are processed to determine the position of the slider in the cut pictures and calculate the pixel spacing between each pair of cut pictures based on this position. In an embodiment of the present invention, processing the cut pictures includes reading the RGB encoding of the cut pictures and performing grayscale processing on the cut pictures according to the RGB code, and the cut pictures are cut frame by frame. In this embodiment of the present invention, the reading of the RGB encoding and the grayscale processing are multi-threaded.

[0090] At step 410, the time interval of each cut picture is determined according to the duration and number of frames of the playback video.

[0091] At step 412, the sliding speed of the slider between each pair of cut pictures is determined based on this time interval and pixel spacing, and the instantaneous acceleration of the slider between each frame is determined based on this sliding speed. In an embodiment of the present invention, the calculated instantaneous acceleration is output in the form of key-value pairs and automatically saved in a list for slicing operations on the data in the list.

[0092] In step 414, it is determined that the slider sliding is made by the machine when the number of times of equal instantaneous acceleration reaches the threshold number of times. In an embodiment of the present invention, the situation where the number of times of equal instantaneous acceleration reaches the threshold number of times includes the situation where the instantaneous acceleration is zero.

[0093] In step 416, when the number of times of equal instantaneous acceleration does not reach the threshold number of times, it is determined whether the slider sliding is made by the machine based on the initial segment acceleration set and the final segment acceleration set of the slider. In an embodiment of the present invention, the initial segment acceleration set and the final segment acceleration set are obtained by slicing the list storing the accelerations, and each instantaneous acceleration in the initial segment acceleration set and the final segment acceleration set is compared one by one to determine whether the slider sliding is made by the machine.

[0094] After step 416, method 400 ends.

[0095] Figure 5 A block diagram of an anti-cracking system 500 for slider verification codes according to an embodiment of the present disclosure is shown.

[0096] Figure 5 The anti-cracking system 500 for slider verification codes in executes each step in the above method 400 through various modules. The system 500 includes an input information acquisition module 502, a slider click position detection module 504, an image processing module 506, a slider acceleration calculation module 508, and a machine sliding detection module 510.

[0097] The input information acquisition module 502 can be configured to obtain the position coordinates of the slider click and generate a playback video of the slider sliding.

[0098] The slider click position detection module 504 can be configured to determine that the slider click is made by the machine when the number of times of the same position coordinates reaches the threshold number of times.

[0099] The image processing module 506 can be configured to decompose the playback video and perform image cutting, and process the cut images to determine the position of the slider in the cut images.

[0100] The slider acceleration calculation module 508 can be configured to calculate the pixel spacing between the sliders in each cut image based on the determined position, determine the time interval of each cut image according to the duration and number of frames of the playback video, and determine the sliding speed of the slider between each cut image based on the time interval and the pixel spacing and determine the instantaneous acceleration of the slider between each frame based on the sliding speed.

[0101] The machine sliding detection module 510 can be configured to determine that the slider sliding is made by the machine when the number of times of equal instantaneous acceleration reaches a threshold number of times, and to determine whether the slider sliding is made by the machine based on the set of initial acceleration and the set of final acceleration of the slider when the number of times of equal instantaneous acceleration does not reach the threshold number of times.

[0102] For most current slider validations, simply dragging the slider to the correct position can pass the validation, or simulations that mimic relatively real human operations can bypass the detection. The advantage of this application is that it performs a full-automatic detection of the sliding slider verification code by analyzing the motion characteristics of the user dragging the slider and comparing the coordinate positions and speed changes during the process of the machine dragging the slider, and has technical reinforcement. This greatly increases the difficulty of machine recognition, prevents the verification code from being cracked, and enables its function of distinguishing between machines and humans to take effect.

[0103] The above has described embodiments of the present invention with reference to the block diagrams and / or operational descriptions of methods, systems, and computer program products according to embodiments of the present invention. The various functions / actions noted in the blocks may occur in a different order than any flowchart shown. For example, depending on the functions / actions involved, two consecutive blocks shown may actually be executed substantially simultaneously, or these blocks may sometimes be executed in the reverse order.

[0104] As described above, only the specific embodiments of the present invention that are better are described, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for preventing cracking of slider verification codes, the method comprises: Obtaining the position coordinates of the slider click and generating a playback video of the slider sliding; Determining that the slider click is made by a machine when the number of times the position coordinates are the same reaches a threshold number of times; Decomposing the playback video and performing picture cutting; Processing the cut pictures to determine the position of the slider in the cut pictures and calculating the pixel spacing between the sliders in each cut picture based on the position; Determining the time interval of each cut picture according to the duration and number of frames of the playback video; Determining the sliding speed of the slider between each cut picture based on the time interval and the pixel spacing and determining the instantaneous acceleration of the slider between each frame based on the sliding speed; Determining that the slider sliding is made by a machine when the number of times the instantaneous accelerations are equal reaches a threshold number of times; and When the number of times the instantaneous accelerations are equal does not reach the threshold number of times, determining whether the slider sliding is made by a machine based on the initial acceleration set and the final acceleration set of the slider.

2. The method according to claim 1, wherein the position coordinates and the playback video are obtained within a predetermined time period, and when it is determined that the slider click is made by a machine, the position coordinates or the IP address of the logged-in machine are stored in a database.

3. The method according to claim 1, further comprising excluding abnormal situations from the playback video.

4. The method according to claim 1, wherein processing the cut pictures includes reading the RGB encoding of the cut pictures and performing grayscale processing on the cut pictures according to the RGB codes, and the cut pictures are cut frame by frame.

5. The method according to claim 4, wherein the reading of the RGB encoding and the grayscale processing are multi-threaded.

6. The method according to claim 1, wherein the instantaneous acceleration is output in the form of key-value pairs and automatically saved to a list for slicing operations on the data in the list.

7. The method according to claim 6, wherein the initial acceleration set and the final acceleration set are obtained by slicing the list, and each instantaneous acceleration in the initial acceleration set and the final acceleration set is compared one by one to determine whether the sliding of the slider is made by a machine.

8. The method according to claim 1, wherein the situation where the number of times the instantaneous accelerations are equal reaches a threshold number of times includes the situation where the instantaneous acceleration is zero.

9. A system for preventing cracking of slider verification codes, the system comprises: An input information collection module configured to obtain the position coordinates of the slider click and generate a playback video of the slider click; A slider click position detection module configured to determine that the slider click is made by a machine when the number of times the position coordinates are the same reaches a threshold number of times; A picture processing module configured to: Decompose the playback video and perform picture cutting; Process the cut pictures to determine the position of the slider in the cut pictures; A slider acceleration calculation module, which is configured to: calculate the pixel pitch between each pair of cut images of the slider based on the position; determine the time interval between each pair of cut images according to the duration and number of frames of the playback video; and determine the sliding speed of the slider between each pair of cut images based on the time interval and the pixel pitch and determine the instantaneous acceleration of the slider between each pair of frames based on the sliding speed; A machine sliding detection module, which is configured to: determine that the sliding of the slider is made by the machine when the number of times the instantaneous accelerations are equal reaches a threshold number of times; judge whether the sliding of the slider is made by the machine based on the initial acceleration set and the final acceleration set of the slider when the number of times the instantaneous accelerations are equal does not reach the threshold number of times.

10. A computer-readable medium storing computer-executable instructions that, when executed, are used to perform the method according to any one of claims 1-8.

Images