WO2022095359A1 - 基于防摄屏的信息安全保护方法、装置、电子设备及介质 - Google Patents

基于防摄屏的信息安全保护方法、装置、电子设备及介质 Download PDF

Info

Publication number
WO2022095359A1
WO2022095359A1 PCT/CN2021/090723 CN2021090723W WO2022095359A1 WO 2022095359 A1 WO2022095359 A1 WO 2022095359A1 CN 2021090723 W CN2021090723 W CN 2021090723W WO 2022095359 A1 WO2022095359 A1 WO 2022095359A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
screen
target detection
confidence
detection model
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.)
Ceased
Application number
PCT/CN2021/090723
Other languages
English (en)
French (fr)
Inventor
顾佳页
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2022095359A1 publication Critical patent/WO2022095359A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/82Protecting input, output or interconnection devices
    • G06F21/84Protecting input, output or interconnection devices output devices, e.g. displays or monitors
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Definitions

  • the present application relates to the technical field of information security, and in particular, to an information security protection method, device, electronic device, and computer-readable storage medium based on an anti-camera screen.
  • the screen-taking method refers to taking pictures of digital information displayed on the screen by using an electronic device with a camera function, so as to achieve the purpose of data theft.
  • An information security protection method based on an anti-screening screen provided by this application includes:
  • the set sampling frequency use the front camera of the electronic device to collect a frame of video signal every preset time, and obtain an image frame according to the video signal;
  • the present application also provides an information security protection device based on an anti-camera screen, the device comprising:
  • an image frame module configured to use the front camera of the electronic device to collect a frame of video signal every preset time according to the set sampling frequency, and obtain an image frame according to the video signal;
  • a confidence module used for using the pre-trained target detection model to perform screen-shot judgment on the image frame to obtain the image confidence
  • a comparison module configured to compare the relationship between the image confidence and a preset reliability threshold, and determine the possibility of a screen-capture operation according to the relationship
  • a security pre-warning module configured to perform pre-warning of information security according to the possibility of the screen-capture operation.
  • the present application also provides an electronic device, the electronic device comprising:
  • the memory stores computer program instructions executable by the at least one processor, the computer program instructions being executed by the at least one processor to enable the at least one processor to perform the Screen information security protection methods:
  • the set sampling frequency use the front camera of the electronic device to collect a frame of video signal every preset time, and obtain an image frame according to the video signal;
  • the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the following information security protection method based on an anti-screening screen:
  • the set sampling frequency use the front camera of the electronic device to collect a frame of video signal every preset time, and obtain an image frame according to the video signal;
  • FIG. 1 is a schematic flowchart of an information security protection method based on an anti-screening screen provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of one of the steps in the information security protection method based on the anti-screening screen shown in FIG. 1;
  • FIG. 3 is a schematic flowchart of another step in the information security protection method based on the anti-screening screen shown in FIG. 1;
  • FIG. 4 is a schematic diagram of a module of an information security protection device based on an anti-screening screen provided by an embodiment of the present application;
  • FIG. 5 is a schematic diagram of an internal structure of an electronic device for implementing an information security protection method based on an anti-screening screen according to an embodiment of the present application.
  • An embodiment of the present application provides an information security protection method based on an anti-screening screen
  • the execution subject of the information security protection method based on an anti-screening screen includes, but is not limited to, a server, a terminal, and the like, which can be configured to execute the methods provided by the embodiments of the present application. at least one of the electronic devices of the method.
  • the information security protection method based on the anti-camera screen can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • FIG. 1 it is a schematic flowchart of an information security protection method based on an anti-screening screen provided by an embodiment of the present application.
  • the information security protection method based on the anti-screening screen is applied to an electronic device including a front camera, and includes:
  • the set sampling frequency use the front camera of the electronic device to collect a frame of video signal every preset time, and obtain an image frame according to the video signal.
  • the sampling frequency may be set according to actual requirements, for example, may be set to one minute.
  • the front camera of the electronic device may be a built-in camera of the electronic device or an on-screen camera.
  • the existing image frame extraction software is used to extract and process the video signal, and an image frame including N continuous shooting images is obtained.
  • N can be set to 3.
  • the target detection model may be three common models based on deep learning target detection: FasterR-CNN, R-FCN, and SSD.
  • the target detection model can extract features from the image, perform probability calculation of the category of the target object according to the extracted features, and output the classification of the target object according to the probability.
  • the pre-trained target detection model is used to judge the image frame by taking a screen shot to obtain the image confidence, including:
  • performing feature extraction on the image frame by using a pre-trained target detection model to obtain a feature image includes: performing convolution processing on the image frame by using a convolution layer of the target detection model to obtain a volume using the activation layer of the target detection model to perform activation processing on the convolutional image to obtain an activation image; using the pooling layer of the target detection model to perform pooling processing on the activation image to obtain a feature image.
  • convolution processing is a linear operation, and performing convolution processing on the image frame can not only eliminate noise and enhance features, but also increase the receptive field, so that the pre-built target detection model can extract more Rich feature information to make up for the loss of internal data structure, loss of spatial level information and other information losses.
  • the convolution processing includes:
  • the image frame is divided in the order from top to bottom and from left to right to obtain the initial sub-image
  • the pixel product values are summed to obtain a target pixel value, and a convolution image is determined according to the target pixel value.
  • the embodiment of the present application uses the activation function to process the convolution image to obtain the activation image.
  • the activation function may be a Sigmoid function, a tanh function, a Relu function, or the like.
  • the activation process can increase the nonlinearity of the target detection network, map the features to a high-dimensional nonlinear interval for interpretation, and solve problems that cannot be solved by a linear model.
  • the pooling process can perform feature selection and information filtering on the activation image. By reducing the dimension of the feature and retaining valid information, overfitting can be avoided to a certain extent, and rotation, translation, and scaling can be maintained without deformation.
  • the pooling process includes:
  • a feature image is obtained.
  • the feature image is classified and probability calculated by using the full connection and the softmax function to obtain the image confidence.
  • the method before the pre-trained target detection model is used to judge the image frame by taking a screen shot to obtain the image confidence, the method further includes:
  • Step A obtaining the training data set and the standard target detection result corresponding to the training data set;
  • Step B inputting the training data set into the target detection model for screen-shot judgment to obtain a training result
  • Step C using a preset loss function to calculate the loss value on the training result and the standard target detection result to obtain the loss value;
  • Step D when the loss value is greater than or equal to the preset loss threshold, it indicates that the output result of the target detection model is not accurate enough, and the parameters of the target detection model need to be adjusted, and then return to the step B;
  • Step E When the loss value is less than the loss threshold, it means that the output result of the target detection model is accurate, and the pre-trained target detection model is obtained.
  • the embodiment of the present application uses the following loss function to calculate the loss value on the training result and the preset target result to obtain the loss value, including:
  • two confidence thresholds may be preset, which are a first confidence threshold and a second confidence threshold, respectively.
  • the comparing the relationship between the image confidence and the preset reliability threshold, and determining the possibility of the screen capture operation according to the relationship includes:
  • the first confidence threshold may be 10, and the second confidence threshold may be 5.
  • an early warning of information security when the possibility of the screen-capturing operation is determined to be screen-capturing or suspected to be screen-capturing, an early warning of information security is performed.
  • the early warning includes the electronic device ringing, or sending early warning information to a preset monitoring terminal, and the like.
  • the embodiment of the present application may also perform a screen capture process on the content currently displayed on the screen of the electronic device to obtain a screen capture image. ;
  • the image frame corresponding to the image after the screenshot is sent to the preset monitoring device, and further locked or logged out The currently logged in user.
  • the image frame corresponding to the possibility of the screen capture operation being a suspected screen capture may also be sent to a preset monitoring device and the corresponding monitoring device is reminded The personnel conducts a second confirmation, and when the possibility of manually confirming the screen capture operation is determined to be the screen capture operation, the operation of locking or logging out the currently logged-in user is performed.
  • the electronic device When it is determined that the possibility of the screen capture operation is that the screen is not captured, the electronic device continues to collect a frame of video signal every preset time, and maintains the normal operation of the screen of the electronic device.
  • FIG. 4 it is a schematic diagram of a module of an information security protection device based on an anti-photographing screen provided by an embodiment of the present application.
  • the information security protection device 100 based on the anti-camera screen described in this application can be installed in an electronic device.
  • the information security protection device 100 based on the anti-screening screen may include an image frame module 101 , a confidence module 102 , a comparison module 103 and a security warning module 104 .
  • the modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can perform fixed functions, and are stored in the memory of the electronic device.
  • each module/unit is as follows:
  • the image frame module 101 is configured to use the front camera of the electronic device to collect a frame of video signal every preset time according to the set sampling frequency, and obtain an image frame according to the video signal;
  • the confidence module 102 is configured to use the pre-trained target detection model to judge the image frame by taking a screen shot to obtain the image confidence;
  • the comparison module 103 is configured to compare the relationship between the image confidence and a preset reliability threshold, and determine the possibility of the screen-capture operation according to the relationship;
  • the security early warning module 104 is configured to perform early warning of information security according to the possibility of the screen capture operation.
  • the information security protection device 100 based on the anti-screening screen when executed by the processor of the electronic device, it can implement an information security protection method based on the anti-screening screen including the following steps:
  • Step 1 The image frame module 101 uses the front camera of the electronic device to collect a frame of video signal every preset time according to the set sampling frequency, and obtains an image frame according to the video signal.
  • the sampling frequency may be set according to actual requirements, for example, may be set to one minute.
  • the front camera of the electronic device may be a built-in camera of the electronic device or an on-screen camera.
  • the image frame module 101 described in this embodiment of the present application uses existing image frame extraction software to extract and process the video signal to obtain an image frame including N continuous shooting images.
  • N can be set to 3.
  • Step 2 The confidence module 102 uses the pre-trained target detection model to perform screen-shot judgment on the image frame to obtain the image confidence.
  • the target detection model may be three common models based on deep learning target detection: FasterR-CNN, R-FCN, and SSD.
  • the target detection model can extract features from the image, perform probability calculation of the category of the target object according to the extracted features, and output the classification of the target object according to the probability.
  • the confidence module 102 uses the following operations to perform screen-shot judgment on the image frame to obtain the image confidence:
  • the feature images are classified and probability calculated by using the pre-trained target detection model, so as to obtain the image confidence about the screen capture operation.
  • the confidence module 102 adopts the following operations to perform feature extraction on the image frame to obtain a feature image: perform convolution processing on the image frame by using the convolution layer of the target detection model to obtain a convolution image; use the activation layer of the target detection model to perform activation processing on the convolutional image to obtain an activation image; use the pooling layer of the target detection model to perform pooling processing on the activation image to obtain a feature image.
  • convolution processing is a linear operation, and performing convolution processing on the image frame can not only eliminate noise and enhance features, but also increase the receptive field, so that the pre-built target detection model can extract more Rich feature information to make up for the loss of internal data structure, loss of spatial level information and other information losses.
  • the convolution processing includes:
  • the image frame is divided in the order from top to bottom and from left to right to obtain the initial sub-image
  • the pixel product values are summed to obtain a target pixel value, and a convolution image is determined according to the target pixel value.
  • the embodiment of the present application uses the activation function to process the convolution image to obtain the activation image.
  • the activation function may be a Sigmoid function, a tanh function, a Relu function, or the like.
  • the activation process can increase the nonlinearity of the target detection network, map the features to a high-dimensional nonlinear interval for interpretation, and solve problems that cannot be solved by a linear model.
  • the pooling process can perform feature selection and information filtering on the activation image. By reducing the dimension of the feature and retaining valid information, overfitting can be avoided to a certain extent, and rotation, translation, and scaling can be maintained without deformation.
  • the pooling process includes:
  • a feature image is obtained.
  • the feature image is classified and probability calculated by using the full connection and the softmax function to obtain the image confidence.
  • the confidence module 102 further performs training of the target detection model.
  • the training process includes:
  • Step A obtaining the training data set and the standard target detection result corresponding to the training data set;
  • Step B inputting the training data set into the target detection model for screen-shot judgment to obtain a training result
  • Step C using a preset loss function to calculate the loss value on the training result and the standard target detection result to obtain the loss value;
  • Step D when the loss value is greater than or equal to the preset loss threshold, it indicates that the output result of the target detection model is not accurate enough, and the parameters of the target detection model need to be adjusted, and then return to the step B;
  • Step E When the loss value is less than the loss threshold, it means that the output result of the target detection model is accurate, and the pre-trained target detection model is obtained.
  • the confidence module 102 in this embodiment of the present application uses the following loss function to calculate the loss value between the training result and the preset target result, and obtain the loss value, including:
  • Step 3 The comparison module 103 compares the relationship between the image confidence level and a preset confidence level threshold, and determines the possibility of a screen capture operation according to the relationship.
  • two confidence thresholds may be preset, which are a first confidence threshold and a second confidence threshold, respectively.
  • the comparison module 103 compares the relationship between the image confidence level and the preset confidence level threshold, and determines the possibility of the screen capture operation according to the relationship, including:
  • the preset confidence threshold includes a first confidence threshold and a second confidence threshold
  • determining the possibility of the screen-capturing operation is determining the screen-capturing operation
  • the image confidence level is less than the second confidence level threshold, it is determined that the possibility of the screen capture operation is that the screen is not captured.
  • the first confidence threshold may be 10, and the second confidence threshold may be 5.
  • Step 4 The security early warning module 104 performs information security early warning according to the possibility of the screen capture operation.
  • an early warning of information security when the possibility of the screen-capturing operation is determined to be screen-capturing or suspected to be screen-capturing, an early warning of information security is performed.
  • the early warning includes the electronic device ringing, or sending early warning information to a preset monitoring terminal, and the like.
  • the security early warning module 104 described in this embodiment of the present application may also perform a screen capture process on the content currently displayed on the screen of the electronic device, to obtain: The image after the screen capture; when the possibility of the screen capture operation is determined to be a confirmed screen capture, or the possibility of the screen capture operation is determined to be a suspected screen capture, the image frame corresponding to the screen capture image is sent to the preset monitoring device, and the Further lock out or log out the currently logged in user.
  • the security warning module 104 may also send the image frame corresponding to the suspected screen capture operation to the preset
  • the monitoring device reminds the corresponding monitoring personnel to perform a second confirmation, and when the possibility of manually confirming the screen capture operation is determined to be the screen capture operation, the operation of locking or logging out the currently logged-in user is performed.
  • the electronic device When it is determined that the possibility of the screen capture operation is that the screen is not captured, the electronic device continues to collect a frame of video signal every preset time, and maintains the normal operation of the screen of the electronic device.
  • FIG. 5 it is a schematic structural diagram of an electronic device implementing an information security protection method based on an anti-screening screen according to the present application.
  • the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as an information security protection program based on an anti-camera screen 12.
  • the memory 11 includes at least one type of readable storage medium, and the readable storage medium may be volatile or non-volatile.
  • the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (eg, SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like.
  • the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1.
  • the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) equipped on the electronic device 1.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 can not only be used to store the application software and various data installed in the electronic device 1, such as the code of the information security protection program 12 based on the anti-camera screen, etc., but also can be used to temporarily store the data that has been output or will be output. data.
  • the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
  • Central processing unit Central Processing unit, CPU
  • microprocessor digital processing chip
  • graphics processor and combination of various control chips, etc.
  • the processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and by running or executing the program or module stored in the memory 11 (for example, executing a The information security protection program of the anti-screening screen, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (extended industry standard architecture, EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.
  • FIG. 5 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 5 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the drawings. components, or a combination of certain components, or a different arrangement of components.
  • the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
  • the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
  • the information security protection program 12 based on the anti-screening screen stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, it can realize:
  • the set sampling frequency use the front camera of the electronic device to collect a frame of video signal every preset time, and obtain an image frame according to the video signal;
  • the modules/units integrated in the electronic device 1 may be stored in a computer-readable storage medium.
  • the computer-readable storage medium may be volatile or non-volatile.
  • the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read Only Memory) -Only Memory).
  • the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function, and the like; The data created by the use of the node, etc.
  • modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

本申请涉及信息安全技术,揭露一种基于防摄屏的信息安全保护方法,包括:根据设定的采样频率,利用电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据视频信号得到图像帧,利用预先训练的目标检测模型对图像帧进行摄屏判断,得到图像置信度,比较图像置信度与预设置信度阈值之间的关系,并根据关系确定摄屏操作的可能性,根据摄屏操作的可能性执行信息安全的预警。本申请还涉及区块链技术,所述图像帧等可以存储在区块链节点中。本申请还揭露一种基于防摄屏的信息安全保护装置、电子设备及存储介质。本申请可以及时发现通过摄屏方式进行信息窃取的行为,以提高信息安全性。

Description

基于防摄屏的信息安全保护方法、装置、电子设备及介质
本申请要求于2020年11月06日提交中国专利局、申请号为202011231145.4,发明名称为“基于防摄屏的信息安全保护方法、装置、电子设备及介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息安全技术领域,尤其涉及一种基于防摄屏的信息安全保护方法、装置、电子设备及计算机可读存储介质。
背景技术
随着信息技术的快速发展,信息泄露情况也越来越严重,目前市面上大部分信息泄露的保护方案都是采用文档操作授权,而文档操作授权主要防止是以数字信息作为载体的信息泄露方式,而对于通过摄屏方式进行数据窃取,却无能为力。所述摄屏方式是指利用具有拍照功能的电子设备对屏幕显示的数字信息进行拍照,从而达到数据窃取的目的。
发明人意识到,对于通过摄屏方式进行数据窃取这一场景,目前只能通过诸如职场监控等事后追溯的方式去追责和止损,即使事后对相关人员进行追责处罚,但是对于已经造成的泄露导致的企业经济、法律、名誉的损失已经实际发生。
发明内容
本申请提供的一种基于防摄屏的信息安全保护方法,包括:
根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
根据所述摄屏操作的可能性执行信息安全的预警。
本申请还提供一种基于防摄屏的信息安全保护装置,所述装置包括:
图像帧模块,用于根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
置信度模块,用于利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
比较模块,用于比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
安全预警模块,用于根据所述摄屏操作的可能性执行信息安全的预警。
本申请还提供一种电子设备,所述电子设备包括:
至少一个处理器;以及,
与所述至少一个处理器通信连接的存储器;其中,
所述存储器存储有可被所述至少一个处理器执行的计算机程序指令,所述计算机程序指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的基于防摄屏的信息安全保护方法:
根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
根据所述摄屏操作的可能性执行信息安全的预警。
本申请还提供一种计算机可读存储介质,存储有计算机程序,所述计算机程序被处理器执行时实现如下所述的基于防摄屏的信息安全保护方法:
根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
根据所述摄屏操作的可能性执行信息安全的预警。
附图说明
图1为本申请实施例提供的基于防摄屏的信息安全保护方法的流程示意图;
图2为图1所示的基于防摄屏的信息安全保护方法中其中一个步骤的流程示意图;
图3为图1所示的基于防摄屏的信息安全保护方法中另外一个步骤的流程示意图;
图4为本申请实施例提供的基于防摄屏的信息安全保护装置的模块示意图;
图5为本申请实施例提供的实现基于防摄屏的信息安全保护方法的电子设备的内部结构示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供一种基于防摄屏的信息安全保护方法,所述基于防摄屏的信息安全保护方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述基于防摄屏的信息安全保护方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
参照图1所示,为本申请实施例提供的一种基于防摄屏的信息安全保护方法的流程示意图。在本实施例中,所述基于防摄屏的信息安全保护方法应用于包括前置摄像头的电子设备中,并包括:
S1、根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧。
本申请实施例中,所述采样频率可以根据实际的需求设定,如可以设定为一分钟。
进一步地,所述电子设备的前置摄像头可以为电子设备的内置摄像头或屏幕外挂式摄像头。
本申请实施例利用现有的图像帧提取软件对所述视频信号进行提取处理,得到包括N张连拍图像的图像帧。较佳地,N可以设置为3。
S2、利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度。
本申请实施例中,所述目标检测模型可以是基于深度学习目标检测的三种常见模型:FasterR-CNN、R-FCN和SSD。所述目标检测模型可以从图像中提取出特征,根据提取的特征执行目标物所属类别的概率计算,并根据所述概率输出所述目标物的分类。
具体地,参阅图2所示,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度,包括:
S21、利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像;
S22、利用所述预先训练的目标检测模型对所述特征图像进行分类及概率计算,得到关于摄屏操作的图像置信度。
详细地,所述利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像,包括:利用所述目标检测模型的卷积层对所述图像帧执行卷积处理,得到卷积图像;利用所述目标检测模型的激活层对所述卷积图像进行激活处理,得到激活图像;利用所述目标检测模型的池化层对所述激活图像进行池化处理,得到特征图像。
其中,卷积处理是一种线性运算,对所述图像帧进行卷积处理不仅可以消除噪声、增强特征,而且可以增大了感受野,从而使得所述预构建的目标检测模型能够提取到更丰富的特征信息,弥补内部数据结构丢失,空间层级信息丢失等信息损失。
详细地,所述卷积处理,包括:
根据预设的卷积核,按照从上往下,从左往右的顺序划分所述图像帧,得到初始子图像;
将所述预设的卷积核与所述初始子图像中的像素值相乘,得到像素乘积值;
对所述像素乘积值进行求和,得到目标像素值,根据所述目标像素值确定卷积图像。
进一步地,所述激活层中有预设的激活函数,本申请实施例利用所述激活函数对卷积图像进行处理,得到激活图像。
其中,所述激活函数可以是Sigmoid函数、tanh函数、Relu函数等。
优选地,所述激活处理可以增加目标检测网络的非线性,将特征映射到高维的非线性区间进行解释,解决线性模型所不能解决的问题。
所述池化处理能对所述激活图像进行特征选择和信息过滤,通过降低特征的维度并保留有效信息,在一定程度上避免过拟合,保持旋转、平移、伸缩不变形。
具体地,所述池化处理包括:
将所述激活图像按照从左至右,从上至下的顺序划分出N*N的区块;
利用所述池化层对所述激活图像中的若干区块进行池化处理,得到特征图像。
进一步地,本申请实施例通过全连接和softmax函数对所述特征图像进行分类及概率计算,得到图像置信度。
本申请另一个实施例中,在所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度之前,所述方法还包括:
步骤A:获取训练数据集和所述训练数据集对应的标准目标检测结果;
步骤B:将所述训练数据集输入至所述目标检测模型进行摄屏判断,得到训练结果;
步骤C:利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值;
步骤D:当所述损失值大于或等于预设的损失阈值时,说明所述目标检测模型的输出结果不够精确,需要调整所述目标检测模型的参数,此时返回至所述步骤B;
步骤E:当所述损失值小于所述损失阈值时,说明所述目标检测模型的输出结果精确,得到所述预先训练完成的目标检测模型。
详细地,本申请实施例利用如下所述损失函数对所述训练结果与预设的目标结果进行损失值计算,得到损失值,包括:
利用下述损失函数计算损失值:
Figure PCTCN2021090723-appb-000001
其中,
Figure PCTCN2021090723-appb-000002
为所述训练结果,Y为所述标准目标检测结果,α表示误差因子,N为所述训练结果的数量,i表示第i个训练结果。。
S3、比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性。
本申请实施例可以预设两个置信度阈值,分别为第一置信度阈值和第二置信度阈值。
参阅图3所示,具体地,所述比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性,包括:
S31、将所述图像置信度与预设置信度阈值进行比较,其中,所述预设置信度阈值包括第一置信度阈值和第二置信度阈值;
S32、在所述图像置信度大于或者等于第一置信度阈值时,判定摄屏操作的可能性为确定摄屏;或
S33、在所述图像置信度小于所述第一置信度阈值且大于或者等于第二置信度阈值时,判定摄屏操作的可能性为疑似摄屏;或
S34、在所述图像置信度小于所述第二置信度阈值时,判定摄屏操作的可能性为未摄屏。
优选地,所述第一置信度阈值可以是10,所述第二置信度阈值可以是5。
S4、根据所述摄屏操作的可能性执行信息安全的预警。
本申请实施例中,当所述摄屏操作的可能性为确定摄屏或者疑似摄屏时,执行信息安全的预警。其中,所述预警包括所述电子设备响铃、或者向预设监控终端发送预警信息等。
进一步地,当判定所述摄屏操作的可能性为确定摄屏或者疑似摄屏时,本申请实施例还可以对所述电子设备的屏幕上当前显示的内容进行截屏处理,得到截屏后的图像;当判定摄屏操作的可能性为确定摄屏,或判定判断摄屏操作的可能性为疑似摄屏,将截屏后的图像所对应的图像帧发送给预设监控设备,并进一步锁定或者注销当前登录用户。
本申请其他实施例中,在判定摄屏操作的可能性为疑似摄屏时,也可以将所述摄屏操作的可能性为疑似摄屏对应的图像帧发送给预设监控设备并提醒对应监控人员进行二次确认,并在人工确认为摄屏操作的可能性为确定摄屏时,再执行锁定或者注销当前登录用户的操作。
在判定摄屏操作的可能性为未摄屏时,所述电子设备继续每隔预设时间采集一帧视频信号,并维持所述电子设备的屏幕正常运行。
如图4所示,是本申请实施例提供的基于防摄屏的信息安全保护装置的模块示意图。
本申请所述基于防摄屏的信息安全保护装置100可以安装于电子设备中。根据实现的功能,所述基于防摄屏的信息安全保护装置100可以包括图像帧模块101、置信度模块102、比较模块103及安全预警模块104。本申请所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述图像帧模块101,用于根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
所述置信度模块102,用于利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
所述比较模块103,用于比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
所述安全预警模块104,用于根据所述摄屏操作的可能性执行信息安全的预警。
详细地,所述基于防摄屏的信息安全保护装置100在由电子设备的处理器所执行时,可以实现包括下述步骤的一种基于防摄屏的信息安全保护方法:
步骤一、所述图像帧模块101根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧。
本申请实施例中,所述采样频率可以根据实际的需求设定,如可以设定为一分钟。
进一步地,所述电子设备的前置摄像头可以为电子设备的内置摄像头或屏幕外挂式摄像头。
本申请实施例所述图像帧模块101利用现有的图像帧提取软件对所述视频信号进行提取处理,得到包括N张连拍图像的图像帧。较佳地,N可以设置为3。
步骤二、所述置信度模块102利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度。
本申请实施例中,所述目标检测模型可以是基于深度学习目标检测的三种常见模型:FasterR-CNN、R-FCN和SSD。所述目标检测模型可以从图像中提取出特征,根据提取的特征执行目标物所属类别的概率计算,并根据所述概率输出所述目标物的分类。
具体地,所述置信度模块102采用下述操作执行对所述图像帧进行摄屏判断,得到图像置信度:
利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像;
利用所述预先训练的目标检测模型对所述特征图像进行分类及概率计算,得到关于摄屏操作的图像置信度。
详细地,所述置信度模块102采用下述操作执行对所述图像帧的特征提取,得到特征图像:利用所述目标检测模型的卷积层对所述图像帧执行卷积处理,得到卷积图像;利用所述目标检测模型的激活层对所述卷积图像进行激活处理,得到激活图像;利用所述目标检测模型的池化层对所述激活图像进行池化处理,得到特征图像。
其中,卷积处理是一种线性运算,对所述图像帧进行卷积处理不仅可以消除噪声、增强特征,而且可以增大了感受野,从而使得所述预构建的目标检测模型能够提取到更丰富的特征信息,弥补内部数据结构丢失,空间层级信息丢失等信息损失。
详细地,所述卷积处理,包括:
根据预设的卷积核,按照从上往下,从左往右的顺序划分所述图像帧,得到初始子图像;
将所述预设的卷积核与所述初始子图像中的像素值相乘,得到像素乘积值;
对所述像素乘积值进行求和,得到目标像素值,根据所述目标像素值确定卷积图像。
进一步地,所述激活层中有预设的激活函数,本申请实施例利用所述激活函数对卷积图像进行处理,得到激活图像。
其中,所述激活函数可以是Sigmoid函数、tanh函数、Relu函数等。
优选地,所述激活处理可以增加目标检测网络的非线性,将特征映射到高维的非线性区间进行解释,解决线性模型所不能解决的问题。
所述池化处理能对所述激活图像进行特征选择和信息过滤,通过降低特征的维度并保留有效信息,在一定程度上避免过拟合,保持旋转、平移、伸缩不变形。
具体地,所述池化处理包括:
将所述激活图像按照从左至右,从上至下的顺序划分出N*N的区块;
利用所述池化层对所述激活图像中的若干区块进行池化处理,得到特征图像。
进一步地,本申请实施例通过全连接和softmax函数对所述特征图像进行分类及概率计算,得到图像置信度。
本申请另一个实施例中,所述置信度模块102还执行训练所述目标检测模型。其中,所述训练过程包括:
步骤A:获取训练数据集和所述训练数据集对应的标准目标检测结果;
步骤B:将所述训练数据集输入至所述目标检测模型进行摄屏判断,得到训练结果;
步骤C:利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值;
步骤D:当所述损失值大于或等于预设的损失阈值时,说明所述目标检测模型的输出结果不够精确,需要调整所述目标检测模型的参数,此时返回至所述步骤B;
步骤E:当所述损失值小于所述损失阈值时,说明所述目标检测模型的输出结果精确,得到所述预先训练完成的目标检测模型。
详细地,本申请实施例所述置信度模块102利用如下所述损失函数对所述训练结果与预设的目标结果进行损失值计算,得到损失值,包括:
利用下述损失函数计算损失值:
Figure PCTCN2021090723-appb-000003
其中,
Figure PCTCN2021090723-appb-000004
为所述训练结果,Y为所述标准目标检测结果,α表示误差因子,N为所述训练结果的数量,i表示第i个训练结果。。
步骤三、所述比较模块103比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性。
本申请实施例可以预设两个置信度阈值,分别为第一置信度阈值和第二置信度阈值。
具体地,参阅图3所示,所述比较模块103比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性,包括:
将所述图像置信度与预设置信度阈值进行比较,其中,所述预设置信度阈值包括第一置信度阈值和第二置信度阈值;
在所述图像置信度大于或者等于所述第一置信度阈值时,判定摄屏操作的可能性为确定摄屏;或
在所述图像置信度小于所述第一置信度阈值且大于或者等于所述第二置信度阈值时,判定摄屏操作的可能性为疑似摄屏;或
在所述图像置信度小于所述第二置信度阈值时,判定摄屏操作的可能性为未摄屏。
优选地,所述第一置信度阈值可以是10,所述第二置信度阈值可以是5。
步骤四、所述安全预警模块104根据所述摄屏操作的可能性执行信息安全的预警。
本申请实施例中,当所述摄屏操作的可能性为确定摄屏或者疑似摄屏时,执行信息安全的预警。其中,所述预警包括所述电子设备响铃、或者向预设监控终端发送预警信息等。
进一步地,当判定摄屏操作的可能性为确定摄屏或者疑似摄屏时,本申请实施例所述安全预警模块104还可以对所述电子设备的屏幕上当前显示的内容进行截屏处理,得到截屏后的图像;当判定摄屏操作的可能性为确定摄屏,或判定判断摄屏操作的可能性为疑似摄屏,将截屏后的图像所对应的图像帧发送给预设监控设备,并进一步锁定或者注销当前登录用户。
本申请其他实施例中,在判定摄屏操作的可能性为疑似摄屏时,所述安全预警模块104也可以将所述摄屏操作的可能性为疑似摄屏对应的图像帧发送给预设监控设备并提醒对应监控人员进行二次确认,并在人工确认为摄屏操作的可能性为确定摄屏时,再执行锁定或者注销当前登录用户的操作。
在判定摄屏操作的可能性为未摄屏时,所述电子设备继续每隔预设时间采集一帧视频信号,并维持所述电子设备的屏幕正常运行。
如图5所示,是本申请实现基于防摄屏的信息安全保护方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如基于防摄屏的信息安全保护程序12。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器 11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(SmartMediaCard,SMC)、安全数字(SecureDigital,SD)卡、闪存卡(FlashCard)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如基于防摄屏的信息安全保护程序12的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(CentralProcessingunit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(ControlUnit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如执行基于防摄屏的信息安全保护程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheralcomponentinterconnect,简称PCI)总线或扩展工业标准结构(extendedindustrystandardarchitecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图5仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图5示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(OrganicLight-EmittingDiode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的基于防摄屏的信息安全保护程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
根据所述摄屏操作的可能性执行信息安全的预警。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述计算机可读存储介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-OnlyMemory)。
进一步地,所述计算机可读存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图表记视为限制所涉及的权利要求。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种基于防摄屏的信息安全保护方法,其中,所述方法应用于电子设备,包括:
    根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
    利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
    比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
    根据所述摄屏操作的可能性执行信息安全的预警。
  2. 如权利要求1所述的基于防摄屏的信息安全保护方法,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度,包括:
    利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像;
    利用所述预先训练的目标检测模型对所述特征图像进行分类及概率计算,得到关于摄屏操作的图像置信度。
  3. 如权利要求2所述的基于防摄屏的信息安全保护方法,其中,所述利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像,包括:
    利用所述目标检测模型的卷积层对所述图像帧执行卷积处理,得到卷积图像;
    利用所述目标检测模型的激活层对所述卷积图像进行激活处理,得到激活图像;
    利用所述目标检测模型的池化层对所述激活图像进行池化处理,得到特征图像。
  4. 如权利要求1所述的基于防摄屏的信息安全保护方法,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度之前,所述方法还包括:
    获取训练数据集和所述训练数据集对应的标准目标检测结果;
    将所述训练数据集输入至初始目标检测模型进行摄屏判断,得到训练结果;
    利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值;
    当所述损失值大于或等于预设的损失阈值时,调整所述目标检测模型的参数,返回至所述将所述训练数据集输入至所述目标检测模型进行摄屏判断,得到训练结果的步骤;
    当所述损失值小于所述损失阈值时,得到所述预先训练完成的目标检测模型。
  5. 如权利要求4所述的基于防摄屏的信息安全保护方法,其中,所述利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值,包括:
    利用下述损失函数计算损失值:
    Figure PCTCN2021090723-appb-100001
    其中,
    Figure PCTCN2021090723-appb-100002
    为所述训练结果,Y为所述标准目标检测结果,α表示误差因子,N为所述训练结果的数量,i表示第i个训练结果。
  6. 如权利要求1至5中任意一项所述的基于防摄屏的信息安全保护方法,其中,所述比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性,包括:
    将所述图像置信度与预设置信度阈值进行比较,其中,所述预设置信度阈值包括第一置信度阈值和第二置信度阈值;
    在所述图像置信度大于或者等于所述第一置信度阈值时,判定摄屏操作的可能性为确定摄屏;或
    在所述图像置信度小于所述第一置信度阈值且大于或者等于所述第二置信度阈值时,判定摄屏操作的可能性为疑似摄屏;或
    在所述图像置信度小于所述第二置信度阈值时,判定摄屏操作的可能性为未摄屏。
  7. 如权利要求6所述的基于防摄屏的信息安全保护方法,其中,所述判定摄屏操作的可能性为确定摄屏,或所述判定摄屏操作的可能性为疑似摄屏之后,所述方法还包括:
    对所述电子设备的屏幕上当前显示的内容进行截屏处理,得到截屏后的图像;
    当判定摄屏操作的可能性为确定摄屏,或判定判断摄屏操作的可能性为疑似摄屏,将截屏后的图像所对应的图像帧发送给预设监控。
  8. 一种基于防摄屏的信息安全保护装置,其中,所述装置包括:
    图像帧模块,用于根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
    置信度模块,用于利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
    比较模块,用于比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
    安全预警模块,用于根据所述摄屏操作的可能性执行信息安全的预警。
  9. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的计算机程序指令,所述计算机程序指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的基于防摄屏的信息安全保护方法:
    根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
    利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
    比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
    根据所述摄屏操作的可能性执行信息安全的预警。
  10. 如权利要求9所述的电子设备,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度,包括:
    利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像;
    利用所述预先训练的目标检测模型对所述特征图像进行分类及概率计算,得到关于摄屏操作的图像置信度。
  11. 如权利要求10所述的电子设备,其中,所述利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像,包括:
    利用所述目标检测模型的卷积层对所述图像帧执行卷积处理,得到卷积图像;
    利用所述目标检测模型的激活层对所述卷积图像进行激活处理,得到激活图像;
    利用所述目标检测模型的池化层对所述激活图像进行池化处理,得到特征图像。
  12. 如权利要求9所述的电子设备,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度之前,所述方法还包括:
    获取训练数据集和所述训练数据集对应的标准目标检测结果;
    将所述训练数据集输入至初始目标检测模型进行摄屏判断,得到训练结果;
    利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值;
    当所述损失值大于或等于预设的损失阈值时,调整所述目标检测模型的参数,返回至所述将所述训练数据集输入至所述目标检测模型进行摄屏判断,得到训练结果的步骤;
    当所述损失值小于所述损失阈值时,得到所述预先训练完成的目标检测模型。
  13. 如权利要求12所述的电子设备,其中,所述利用预设的损失函数对所述训练结果 与标准目标检测结果进行损失值计算,得到损失值,包括:
    利用下述损失函数计算损失值:
    Figure PCTCN2021090723-appb-100003
    其中,
    Figure PCTCN2021090723-appb-100004
    为所述训练结果,Y为所述标准目标检测结果,α表示误差因子,N为所述训练结果的数量,i表示第i个训练结果。
  14. 如权利要求9至13中任意一项所述的电子设备,其中,所述比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性,包括:
    将所述图像置信度与预设置信度阈值进行比较,其中,所述预设置信度阈值包括第一置信度阈值和第二置信度阈值;
    在所述图像置信度大于或者等于所述第一置信度阈值时,判定摄屏操作的可能性为确定摄屏;或
    在所述图像置信度小于所述第一置信度阈值且大于或者等于所述第二置信度阈值时,判定摄屏操作的可能性为疑似摄屏;或
    在所述图像置信度小于所述第二置信度阈值时,判定摄屏操作的可能性为未摄屏。
  15. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下所述的基于防摄屏的信息安全保护方法:
    根据设定的采样频率,利用所述电子设备的前置摄像头每隔预设时间采集一帧视频信号,根据所述视频信号得到图像帧;
    利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度;
    比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性;
    根据所述摄屏操作的可能性执行信息安全的预警。
  16. 如权利要求15所述的计算机可读存储介质,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度,包括:
    利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像;
    利用所述预先训练的目标检测模型对所述特征图像进行分类及概率计算,得到关于摄屏操作的图像置信度。
  17. 如权利要求16所述的计算机可读存储介质,其中,所述利用预先训练完成的目标检测模型对所述图像帧执行特征提取,得到特征图像,包括:
    利用所述目标检测模型的卷积层对所述图像帧执行卷积处理,得到卷积图像;
    利用所述目标检测模型的激活层对所述卷积图像进行激活处理,得到激活图像;
    利用所述目标检测模型的池化层对所述激活图像进行池化处理,得到特征图像。
  18. 如权利要求15所述的计算机可读存储介质,其中,所述利用预先训练完成的目标检测模型对所述图像帧进行摄屏判断,得到图像置信度之前,所述方法还包括:
    获取训练数据集和所述训练数据集对应的标准目标检测结果;
    将所述训练数据集输入至初始目标检测模型进行摄屏判断,得到训练结果;
    利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值;
    当所述损失值大于或等于预设的损失阈值时,调整所述目标检测模型的参数,返回至所述将所述训练数据集输入至所述目标检测模型进行摄屏判断,得到训练结果的步骤;
    当所述损失值小于所述损失阈值时,得到所述预先训练完成的目标检测模型。
  19. 如权利要求18所述的计算机可读存储介质,其中,所述利用预设的损失函数对所述训练结果与标准目标检测结果进行损失值计算,得到损失值,包括:
    利用下述损失函数计算损失值:
    Figure PCTCN2021090723-appb-100005
    其中,
    Figure PCTCN2021090723-appb-100006
    为所述训练结果,Y为所述标准目标检测结果,α表示误差因子,N为所述训练结果的数量,i表示第i个训练结果。
  20. 如权利要求15至19中任意一项所述的计算机可读存储介质,其中,所述比较所述图像置信度与预设置信度阈值之间的关系,并根据所述关系确定摄屏操作的可能性,包括:
    将所述图像置信度与预设置信度阈值进行比较,其中,所述预设置信度阈值包括第一置信度阈值和第二置信度阈值;
    在所述图像置信度大于或者等于所述第一置信度阈值时,判定摄屏操作的可能性为确定摄屏;或
    在所述图像置信度小于所述第一置信度阈值且大于或者等于所述第二置信度阈值时,判定摄屏操作的可能性为疑似摄屏;或
    在所述图像置信度小于所述第二置信度阈值时,判定摄屏操作的可能性为未摄屏。
PCT/CN2021/090723 2020-11-06 2021-04-28 基于防摄屏的信息安全保护方法、装置、电子设备及介质 Ceased WO2022095359A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011231145.4 2020-11-06
CN202011231145.4A CN112347526A (zh) 2020-11-06 2020-11-06 基于防摄屏的信息安全保护方法、装置、电子设备及介质

Publications (1)

Publication Number Publication Date
WO2022095359A1 true WO2022095359A1 (zh) 2022-05-12

Family

ID=74429442

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090723 Ceased WO2022095359A1 (zh) 2020-11-06 2021-04-28 基于防摄屏的信息安全保护方法、装置、电子设备及介质

Country Status (2)

Country Link
CN (1) CN112347526A (zh)
WO (1) WO2022095359A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115049760A (zh) * 2022-08-16 2022-09-13 杭州海康威视数字技术股份有限公司 一种基于摩尔效应增强的视频隐私保护方法、装置及设备
CN116927619A (zh) * 2023-07-20 2023-10-24 中国工商银行股份有限公司 针对保险箱的报警方法、装置、电子设备及存储介质
CN117036831A (zh) * 2023-10-09 2023-11-10 视睿(杭州)信息科技有限公司 一种基于时序特征建模闪屏检测方法、系统及介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112347526A (zh) * 2020-11-06 2021-02-09 平安科技(深圳)有限公司 基于防摄屏的信息安全保护方法、装置、电子设备及介质
CN113536980B (zh) * 2021-06-28 2025-03-14 浙江大华技术股份有限公司 拍摄行为检测方法、装置、电子装置和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784653A (zh) * 2017-11-06 2018-03-09 山东浪潮云服务信息科技有限公司 一种防偷拍系统及方法
CN110443136A (zh) * 2019-07-04 2019-11-12 北京九天翱翔科技有限公司 一种全智能电脑显示屏防手机偷拍系统
CN111523384A (zh) * 2020-03-19 2020-08-11 浙江省北大信息技术高等研究院 一种基于视觉的会议防偷拍方法、装置、存储介质及终端
CN111711794A (zh) * 2020-06-22 2020-09-25 上海辰珅科技有限公司 防偷拍图像处理方法、装置、终端及存储介质
CN111832458A (zh) * 2020-07-02 2020-10-27 西安科芮智盈信息技术有限公司 防窃照方法及系统
CN112347526A (zh) * 2020-11-06 2021-02-09 平安科技(深圳)有限公司 基于防摄屏的信息安全保护方法、装置、电子设备及介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111046717B (zh) * 2019-10-11 2024-01-30 平安科技(深圳)有限公司 眼底图像黄斑中心定位方法、装置、电子设备及存储介质
CN111581679A (zh) * 2020-05-06 2020-08-25 台州智必安科技有限责任公司 一种基于深度网络的防范屏幕拍照方法
CN111639704A (zh) * 2020-05-28 2020-09-08 深圳壹账通智能科技有限公司 目标识别方法、装置及计算机可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784653A (zh) * 2017-11-06 2018-03-09 山东浪潮云服务信息科技有限公司 一种防偷拍系统及方法
CN110443136A (zh) * 2019-07-04 2019-11-12 北京九天翱翔科技有限公司 一种全智能电脑显示屏防手机偷拍系统
CN111523384A (zh) * 2020-03-19 2020-08-11 浙江省北大信息技术高等研究院 一种基于视觉的会议防偷拍方法、装置、存储介质及终端
CN111711794A (zh) * 2020-06-22 2020-09-25 上海辰珅科技有限公司 防偷拍图像处理方法、装置、终端及存储介质
CN111832458A (zh) * 2020-07-02 2020-10-27 西安科芮智盈信息技术有限公司 防窃照方法及系统
CN112347526A (zh) * 2020-11-06 2021-02-09 平安科技(深圳)有限公司 基于防摄屏的信息安全保护方法、装置、电子设备及介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115049760A (zh) * 2022-08-16 2022-09-13 杭州海康威视数字技术股份有限公司 一种基于摩尔效应增强的视频隐私保护方法、装置及设备
CN115049760B (zh) * 2022-08-16 2022-12-02 杭州海康威视数字技术股份有限公司 一种基于摩尔效应增强的视频隐私保护方法、装置及设备
CN116927619A (zh) * 2023-07-20 2023-10-24 中国工商银行股份有限公司 针对保险箱的报警方法、装置、电子设备及存储介质
CN117036831A (zh) * 2023-10-09 2023-11-10 视睿(杭州)信息科技有限公司 一种基于时序特征建模闪屏检测方法、系统及介质
CN117036831B (zh) * 2023-10-09 2024-03-22 视睿(杭州)信息科技有限公司 一种基于时序特征建模闪屏检测方法、系统及介质

Also Published As

Publication number Publication date
CN112347526A (zh) 2021-02-09

Similar Documents

Publication Publication Date Title
WO2022095359A1 (zh) 基于防摄屏的信息安全保护方法、装置、电子设备及介质
CN112137591B (zh) 基于视频流的目标物位置检测方法、装置、设备及介质
CN112528908B (zh) 活体检测方法、装置、电子设备及存储介质
US11080553B2 (en) Image search method and apparatus
WO2011159525A1 (en) Object detection metadata
CN110717929B (zh) 图像目标检测方法、装置及存储介质
WO2017114168A1 (en) Method and device for target detection
CN110008997A (zh) 图像纹理相似度识别方法、装置及计算机可读存储介质
CN111950523A (zh) 基于航拍的船只检测优化方法、装置、电子设备及介质
KR102348368B1 (ko) 머신러닝 모델의 학습 데이터 생성과 머신러닝 모델을 이용한 유사 이미지 생성을 위한 장치, 방법, 시스템 및 컴퓨터 판독가능 저장 매체
CN106254807A (zh) 提取静止图像的电子设备和方法
CN118657736A (zh) 一种基于差分背景建模的滴漏检测方法、产品及设备
CN110287767A (zh) 可防攻击的活体检测方法、装置、计算机设备及存储介质
CN113780077A (zh) 基于目标检测的作业行为规范检测方法、装置及终端设备
WO2023134080A1 (zh) 相机作弊识别方法、装置、设备及存储介质
CN110263741A (zh) 视频帧提取方法、装置及终端设备
CN112633183A (zh) 影像遮挡区域自动检测方法、装置及存储介质
CN117094972B (zh) 一种基于高阶空间交互的轻量化pcb缺陷检测方法和系统
CN114758403B (zh) 疲劳驾驶智能分析方法及装置
CN116030493B (zh) 基于事件数据的人形检测方法、装置、设备及存储介质
CN114827706B (zh) 图像处理的方法、计算机程序产品、电子设备及存储介质
CN114973380A (zh) 优化MTCNN和Facenet的人脸识别方法及装置
WO2022227191A1 (zh) 非主动活体检测方法、装置、电子设备及存储介质
CN115439772A (zh) 视频分析方法、装置、计算机设备和存储介质
CN114550072A (zh) 基于烟雾识别的烟草事故报警方法、装置、设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21888063

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21888063

Country of ref document: EP

Kind code of ref document: A1