CN115829687A - Platform transaction safety detection system based on big data - Google Patents
Platform transaction safety detection system based on big data Download PDFInfo
- Publication number
- CN115829687A CN115829687A CN202211619938.2A CN202211619938A CN115829687A CN 115829687 A CN115829687 A CN 115829687A CN 202211619938 A CN202211619938 A CN 202211619938A CN 115829687 A CN115829687 A CN 115829687A
- Authority
- CN
- China
- Prior art keywords
- data
- detection data
- transaction
- detection
- platform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 130
- 230000009471 action Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000000977 initiatory effect Effects 0.000 claims abstract description 5
- 238000004891 communication Methods 0.000 claims description 20
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 description 34
- 238000004364 calculation method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004883 computer application Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000009666 routine test Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the field of security detection, and discloses a platform transaction security detection system based on big data, which comprises a user side and a transaction platform; the user side is used for acquiring the conventional detection data and the action detection data and sending the conventional detection data and the action detection data to the transaction platform; the conventional detection data comprises an IP address, a device mac address and a device type; the action detection data comprises click information of a user in the process from the user opening the user terminal to the transaction request initiation; the transaction platform is used for judging whether the current transaction environment is safe or not based on the detection data and the action detection data. Compared with the existing safety detection items, the method and the system also acquire the click information, and can improve the safety of the online shopping platform by carrying out safety detection on the click information.
Description
Technical Field
The invention relates to the field of security detection, in particular to a platform transaction security detection system based on big data.
Background
In the transaction process of the online shopping platform, the account number of the user may be stolen or the digital certificate may be stolen. In this case, the account of the user may be falsely used by others, and operations that do not meet the user's intention, such as canceling an order that has been placed, modifying a shipping address of the order, and the like, may be performed.
The existing online shopping platform safety detection generally judges whether the transaction is safe by detecting data such as a common IP address of a user, identification information of common equipment and the like. But the IP address and the identification information of the common equipment can be modified, and the security is still not high enough.
Disclosure of Invention
The invention aims to disclose a platform transaction safety detection system based on big data, which solves the problem that the safety is still not high enough because the IP address and the identification information of common equipment can be modified when the existing online shopping platform carries out safety detection based on the IP address and the identification information of the common equipment.
In order to achieve the purpose, the invention adopts the following technical scheme:
a platform transaction safety detection system based on big data comprises a user side and a transaction platform;
the user side is used for acquiring the conventional detection data and the action detection data and sending the conventional detection data and the action detection data to the transaction platform;
the conventional detection data comprises an IP address, a device mac address and a device type;
the action detection data comprises click information of a user in the process from the user opening the user terminal to the transaction request initiation;
the transaction platform is used for judging whether the current transaction environment is safe or not based on the detection data and the action detection data.
Optionally, the click information includes a click position and a click time.
Optionally, the user side includes a first collection module and a second collection module;
the first collection module is used for acquiring conventional detection data;
the second collection module is used for acquiring motion detection data.
Optionally, the user side further includes a first communication module;
the first communication module is used for sending the conventional detection data and the action detection data to the transaction platform.
Optionally, the first communication module includes a network card or a wireless radio frequency chip.
Optionally, the transaction platform includes a second communication module and a storage module;
the second communication module is used for receiving conventional detection data and action detection data sent by the user side;
the storage module is used for storing the conventional detection data and the action detection data received by the second communication module.
Optionally, the storage module is further configured to store the security detection model.
Optionally, the transaction platform further comprises a detection module;
the detection module is used for inputting the conventional detection data and the action detection data into the safety detection model for detection to obtain a safety detection result.
Optionally, the trading platform further comprises an input module;
and the input module is used for modifying the safety detection rules stored in the storage module by a manager with modification authority.
Optionally, the device type includes any one of a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a kiosk.
Compared with the existing platform transaction safety detection items, the online shopping platform and the online shopping method have the advantages that the click information is also acquired, the click habit difference among different users is large, and therefore people who illegally acquire the online shopping account number for illegal operation are difficult to imitate the original click habit of the user, and therefore the safety of the online shopping platform can be improved by carrying out safety detection on the click information.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic diagram of a big data-based platform transaction security detection system according to the present invention.
Fig. 2 is a schematic diagram of a ue according to the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
As shown in fig. 1, in an embodiment, the present invention provides a platform transaction security detection system based on big data, which includes a user terminal 101 and a transaction platform 102;
the user side 101 is used for acquiring conventional detection data and motion detection data and sending the conventional detection data and the motion detection data to the transaction platform 102;
the conventional detection data comprises an IP address, a device mac address and a device type;
the action detection data comprises click information of the user in the process from the user opening the user terminal 101 to the transaction request initiation;
the trading platform 102 is configured to determine whether the current trading environment is safe based on the detection data and the action detection data.
Compared with the existing platform transaction safety detection items, the online shopping platform and the online shopping method have the advantages that the click information is also acquired, the click habit difference among different users is large, and therefore people who illegally acquire the online shopping account number for illegal operation are difficult to imitate the original click habit of the user, and therefore the safety of the online shopping platform can be improved by carrying out safety detection on the click information.
Specifically, the click information includes information of a mouse click or information of a finger click on the touch screen.
When the user uses the equipment with the mouse, the obtained click information is information clicked by the mouse, when the user uses the equipment with the touch screen, the obtained click information is information clicked by a finger on the touch screen, and when the user uses the computer with the touch function, the obtained click information is still information clicked by the mouse.
Specifically, the time of initiating the transaction request is the time of clicking and settling the account after the user adds the commodity into the shopping cart to prepare for payment.
Optionally, the click information includes a click position and a click time.
Specifically, when the click information is click information of a mouse, the click information may further include a dwell time of a pointer of the mouse at different positions.
Optionally, as shown in fig. 2, the user terminal 101 includes a first collection module 111 and a second collection module 112;
the first collection module 111 is used for acquiring conventional detection data;
the second collection module 112 is used to obtain motion detection data.
Alternatively, when the user uses a device with a mouse, the second collection module 112 may include a process of executing a GetCursorPos () function, through which the position information of the mouse is acquired.
Alternatively, when the user uses a device with a touch screen, then the second collection module 112 may include a touch screen driver or a process that executes a getevent command.
Optionally, the user terminal 101 further includes a first communication module;
the first communication module is configured to send the routine test data and the motion test data to the transaction platform 102.
Optionally, the first communication module includes a network card or a wireless radio frequency chip.
Optionally, the trading platform 102 includes a second communication module and a storage module;
the second communication module is used for receiving conventional detection data and motion detection data sent by the user side 101;
the storage module is used for storing the conventional detection data and the action detection data received by the second communication module.
Specifically, the transaction platform 102 may include a cloud server, and the cloud server includes a storage module and a second communication module. At this time, the second communication module includes a port and an API of the cloud server.
Optionally, the storage module is further configured to store the security detection model.
Specifically, the safety detection model is a neural network model obtained by performing big data training by using historical conventional detection data and motion detection data of a user. The longer the service time of the user is, the more click data are acquired, and the higher the safety detection accuracy of the obtained neural network model is.
Optionally, the trading platform 102 further comprises a detection module;
the detection module is used for inputting the conventional detection data and the action detection data into the safety detection model for detection to obtain a safety detection result.
Specifically, when the conventional detection data and the motion detection data both meet the set requirements, the safety detection result indicates that the current transaction passes the safety detection. And when the conventional detection data or the action detection data do not meet the set requirement, the safety detection result indicates that the current transaction does not pass the safety detection.
For example, the detection items of the regular detection data may include: whether the IP address is an IP address of a region that has been frequently registered recently, whether the mac address of the device has changed, whether the type of the device has changed,
when the IP address is the IP address of the area which is frequently logged in recently, the mac address of the equipment is not changed, and the type of the equipment is not changed, the conventional detection data are in accordance with the set requirement.
Judging whether the action detection data meet the set detection requirement, if so, comparing a set U of a binary group < position, time > consisting of the click position and the click time with a comparison set cmpU obtained according to the calculation of the historical click position and the click time of the user by using a neural network model to obtain the correlation between the two sets, and judging whether the correlation meets the set requirement by judging whether the correlation is larger than a set threshold value.
The comparison set is a set obtained by performing linear fitting on data in the binary group obtained according to the historical motion detection data of the user.
For example, the first element in the comparison set cmpU represents the location of the first click after the user opens the user terminal and the click time, where the click time is the time between opening the user terminal and the first click.
And the second element may be the location of the second click and the time of the click. The click time here is the time elapsed from the first click.
Because each user has a corresponding clicking habit in use, whether the user belongs to the same user can be judged by judging the correlation between the latest action detection data and the action detection data subjected to linear fitting.
Optionally, the trading platform 102 further comprises an input module;
and the input module is used for modifying the safety detection rules stored in the storage module by a manager with modification authority.
Optionally, the input module includes a biometric feature obtaining unit, a calculating unit, a comparing unit and an input unit;
the biological characteristic acquisition unit is used for acquiring a biological characteristic image of a manager;
the computing unit is used for acquiring the characteristics of the identification area of the biological characteristic image;
the comparison unit is used for comparing the characteristics acquired by the calculation unit with the characteristics of the identification area of the biological characteristic image of the manager with the modification authority and judging whether the manager has the modification authority;
the input unit is used for modifying the safety detection rules stored in the storage module by a manager with modification authority.
Optionally, the biometric image comprises a face image or a fingerprint image.
Optionally, obtaining the feature of the identification region of the biometric image includes:
carrying out image segmentation on the biological characteristic image to obtain an identification area in the biological characteristic image;
features in the identified region are obtained using a feature extraction algorithm.
Optionally, the image segmentation is performed on the biometric image to obtain an identification region in the biometric image, and the method includes:
carrying out filtering calculation on the biological characteristic image to obtain a filtering image:
acquiring a gray level image imggr of the biological characteristic image;
acquiring a brightness image imgli of the biological characteristic image in a Lab color space;
filtering the gray level image imggr to obtain a first image firph;
filtering the luminance image imgli to obtain a second image sedph;
the filtered image is acquired using the following function:
filph＝λ×firph+(1-λ)×sedph×Φ
wherein, λ represents a filter parameter, λ ∈ (0, 1), Φ represents a mapping coefficient, and is used for expanding a value range of a pixel value in the sedph from [0,100] to [0,255]; filtering represents a filtering image;
and carrying out image segmentation on the filtered image by using a segmentation algorithm to obtain an interested area in the filtered image, and taking the interested area as an identification area.
By performing filtering calculation in different color spaces and then fusing the results of the filtering calculation, the influence of color factors on the filtering result can be effectively reduced and the accuracy of the filtering result is improved because the brightness component only contains brightness information.
Optionally, the filtering processing is performed on the grayscale image imggr to obtain a first image firph, including:
and (4) calculating imggr by using an NLmeans algorithm to obtain the firph.
Optionally, the filtering processing is performed on the luminance image imgli to obtain a second image sedph, including:
calculating imgli by using a Canny algorithm to obtain an edge image;
performing filtering calculation on the edge image by using a bilateral filtering algorithm to obtain a first filtering image;
obtaining a second filtered image by imgli processing as follows:
performing wavelet decomposition on imgli to obtain a wavelet high-frequency coefficient thrso and a wavelet low-frequency coefficient thrst;
and performing filtering calculation on the thrso by using the following function to obtain a calculated wavelet high-frequency coefficient thrsof:
if the value of thrso is greater than or equal to shr, then
If | thrso<shr, then
In the formula, w 1 And w 2 Respectively representing a first and a second adjustment factor, w 3 Representing the filter coefficient, w 4 Representing control coefficients, shr representing calculation thresholds, w 5 Representing the calculated coefficient, w 6 Represents the back-compensation coefficient, w 1 ∈(0.5,0.6)，w 2 ∈(0.1,0.2)，w 3 ∈(0.2,0.3)，w 4 ∈(2,11)，w 5 ∈(0.5,0.6)，w 6 ∈(0.2,0.9)；
Reconstructing the thrsof and the thrst to obtain a second filtering image;
and optimizing the pixel values of the pixel points in the second filtered image based on the first filtered image to obtain a second image sedph.
In the process of acquiring the second image, filtering calculation is not directly performed on imgli, the first filtering image and the second filtering image are respectively acquired, and then pixel points in the second filtering image are optimized through the first filtering image, so that the finally obtained boundary information in the second image is improved, and after the boundary information is improved, the accuracy of subsequent image segmentation is improved.
Specifically, for the first filtered image, the invention directly uses the bilateral filtering algorithm to carry out filtering processing, and can effectively reserve the image boundary information in the first filtered image. For the second filtering image, the filtering result is obtained by performing wavelet denoising processing on imgli, and in the process of wavelet denoising, corresponding filtering functions are selected for wavelet high-frequency coefficients distributed by different pixel values through calculating threshold values to perform filtering calculation, so that the accuracy of the filtering result is improved.
Optionally, optimizing a pixel value of a pixel point in the second filtered image based on the first filtered image to obtain a second image sedph, including:
acquiring a set simset of pixel points of which the pixel values are greater than a set pixel value threshold value in a first filtering image;
acquiring a set timeset of pixel points in the second filtered image, wherein the pixel points have the same coordinates as those in the simset;
for a pixel point pixnd in the timeset, optimizing the pixel value of pixnd by using the following function:
wherein, afval pixnd Indicating the pixel value, fval, after pixnd has been optimized pixnd,one Indicating the pixel value of pixnd in the second filtered image, fval pixnd,two Representing the pixel value of a pixel point in the first filtering image, wherein the pixel point has the same pixnd coordinate; theta () represents a span control coefficient for passing afval pixnd Is controlled to be [0,255]]。
In the optimization process, the boundary information in the first filtering image is mainly added into the second filtering image, so that the boundary information of the second filtering image is promoted.
Optionally, the device type includes any one of a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a kiosk.
Specifically, when the device type is any one of a notebook computer, a desktop computer, and an all-in-one machine, the client is a web page of the online shopping platform or a computer application terminal.
When the device type is any one of a mobile phone and a tablet computer, the client can be an APP or a webpage.
A corresponding listening event may be set in the web page to obtain click information.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A platform transaction safety detection system based on big data is characterized by comprising a user side and a transaction platform;
the user side is used for acquiring the conventional detection data and the action detection data and sending the conventional detection data and the action detection data to the transaction platform;
the conventional detection data comprises an IP address, a device mac address and a device type;
the action detection data comprises click information of a user in the process from the user opening the user terminal to the transaction request initiation;
the transaction platform is used for judging whether the current transaction environment is safe or not based on the detection data and the action detection data.
2. The big-data based platform transaction security detection system of claim 1, wherein the click information comprises click location and click time.
3. The big-data-based platform transaction security detection system according to claim 1, wherein the user side comprises a first collection module and a second collection module;
the first collection module is used for acquiring conventional detection data;
the second collection module is used for acquiring motion detection data.
4. The big data based platform transaction security detection system of claim 3, wherein the user side further comprises a first communication module;
the first communication module is used for sending the conventional detection data and the action detection data to the transaction platform.
5. The big data-based platform transaction security detection system of claim 4, wherein the first communication module comprises a network card or a wireless radio frequency chip.
6. The big data based platform transaction security detection system of claim 1, wherein the transaction platform comprises a second communication module and a storage module;
the second communication module is used for receiving conventional detection data and action detection data sent by the user side;
the storage module is used for storing the conventional detection data and the action detection data received by the second communication module.
7. The big data based platform transaction security detection system of claim 6, wherein the storage module is further configured to store a security detection model.
8. The big data based platform transaction security detection system of claim 7, wherein the transaction platform further comprises a detection module;
the detection module is used for inputting the conventional detection data and the action detection data into the safety detection model for detection to obtain a safety detection result.
9. The big-data-based platform transaction security detection system of claim 7, wherein the transaction platform further comprises an input module;
and the input module is used for modifying the safety detection rules stored in the storage module by a manager with modification authority.
10. The big-data-based platform transaction security detection system according to claim 1, wherein the device type includes any one of a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a kiosk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211619938.2A CN115829687A (en) | 2022-12-15 | 2022-12-15 | Platform transaction safety detection system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211619938.2A CN115829687A (en) | 2022-12-15 | 2022-12-15 | Platform transaction safety detection system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115829687A true CN115829687A (en) | 2023-03-21 |
Family
ID=85545960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211619938.2A Pending CN115829687A (en) | 2022-12-15 | 2022-12-15 | Platform transaction safety detection system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829687A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389704A (en) * | 2015-11-16 | 2016-03-09 | 小米科技有限责任公司 | Method and device for judging authenticity of users |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| US20210209606A1 (en) * | 2020-01-05 | 2021-07-08 | Obsecure Inc. | System, Device, and Method of User Authentication and Transaction Verification |
| CN113256300A (en) * | 2021-05-27 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Transaction processing method and device |
-
2022
- 2022-12-15 CN CN202211619938.2A patent/CN115829687A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389704A (en) * | 2015-11-16 | 2016-03-09 | 小米科技有限责任公司 | Method and device for judging authenticity of users |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| US20210209606A1 (en) * | 2020-01-05 | 2021-07-08 | Obsecure Inc. | System, Device, and Method of User Authentication and Transaction Verification |
| CN113256300A (en) * | 2021-05-27 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Transaction processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 李洋: ""图像边缘检测技术在人脸中的研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 May 2014 (2014-05-15), pages 7 - 25 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107292287B (en) | Face identification method, device, electronic equipment and storage medium | |
| US9715616B2 (en) | Fingerprint sensing and enrollment | |
| CN108229297B (en) | Face recognition method and device, electronic equipment and computer storage medium | |
| WO2017174010A1 (en) | A method for fingerprint unlocking and terminal | |
| Gragnaniello et al. | Iris liveness detection for mobile devices based on local descriptors | |
| US9202099B2 (en) | Fingerprint sensing and enrollment | |
| CN110852160A (en) | Image-based biometric identification system and computer-implemented method | |
| CN111368635B (en) | Millimeter wave-based multi-person gait recognition method and device | |
| WO2018082011A1 (en) | Living fingerprint recognition method and device | |
| CN105279405A (en) | Keypress behavior pattern construction and analysis system of touch screen user and identity recognition method thereof | |
| CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
| EP3364325A1 (en) | Segment-based manual signature authentication system and method | |
| CN105740707A (en) | Malicious file identification method and device | |
| US20220391913A1 (en) | Techniques to improve fraud detection at financial terminals | |
| WO2017156963A1 (en) | Method for fingerprint unlocking, and terminal | |
| CN107451444A (en) | Solve lock control method and Related product | |
| US9158381B2 (en) | Multi-resolution gesture recognition | |
| CN113486377A (en) | Image encryption method and device, electronic equipment and readable storage medium | |
| CN111680664B (en) | Face image age identification method, device and equipment | |
| CN108491142B (en) | Control method of mobile terminal, mobile terminal and storage medium | |
| CN111445058A (en) | Data analysis method, device, equipment and computer readable storage medium | |
| Chen et al. | Image splicing localization using residual image and residual-based fully convolutional network | |
| CN103870812A (en) | Method and system for acquiring palmprint image | |
| CN114329405A (en) | Online operation marketing popularization system | |
| CN111080665A (en) | Image frame identification method, device and equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |