High-energy-efficiency space-time correlation distributed sensing node security anti-attack verification method

Abstract

The invention discloses a high-energy-efficiency space-time correlation distributed sensing node security anti-attack verification method, and aims at low power consumption and high-efficiency security enhancement of mass distributed deployment sensing nodes. The method comprises a low-power-consumption data transmission unit, a spatial neighborhood information fusion sensing data correction unit, a self-adaptive sensing information trend prediction time sequence security copy generation unit, a micro-power-consumption self-adaptive data acquisition unit, a self-adaptive difference value trigger anomaly detection unit, a self-adaptive data integrity verification unit, a self-adaptive data integrity recovery unit and the like. When the system runs, the gateway forms a time sequence-neighborhood fusion security copy according to a multi-node weighted data change rule, judges whether current sensing data is tampered or not on the basis of the time sequence-neighborhood fusion security copy, and corrects error data. And meanwhile, the gateway optimizes the node working mode in real time according to the node sensing data change trend characteristics contained in the security copy, so that the data security is improved, the power consumption is further reduced, the service life of a battery is prolonged, and large-scale application is promoted.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things node control, and in particular to a high-energy-efficiency time-space correlation distributed sensor node security anti-attack verification method. Background Art

[0002] The Internet of Things (IoT) system relies on a large number of distributed sensor nodes to achieve extensive perception and data collection in the physical world, supporting applications in smart cities, smart homes, industrial monitoring and other fields. However, with the rapid development of IoT technology and the continuous expansion of deployment scale, sensor nodes face two key challenges in practical applications: low power optimization and data security. The effective solution to these problems is related to the stability, operation efficiency and privacy protection of user data of the IoT system.

[0003] Specifically, first, low power optimization is a core requirement for efficient operation of IoT sensor nodes. Since IoT nodes usually rely on batteries for power supply, extending battery life directly affects the long-term reliability and operation and maintenance costs of the system. In a widely distributed node network, low power optimization can help sensor nodes significantly reduce energy consumption and reduce the frequency of battery replacement, thereby reducing the operation and maintenance burden and subsequent costs in remote or difficult to maintain environments. However, the resources of sensor nodes are limited, and how to achieve low power consumption while performing multiple tasks has become a technical difficulty.

[0004] Second, IoT sensor nodes will acquire and transmit a large amount of environmentally sensitive data during long-term operation, such as the indoor temperature of smart homes and the traffic conditions of smart cities. This information contains user privacy and important environmental conditions. Since sensor nodes have potential security risks in every link of data collection, transmission and processing, malicious attackers may steal, tamper with or forge sensor data, resulting in information leakage or system misjudgment, which in turn poses a threat to user privacy and system stability. Therefore, data security is crucial to the normal operation of IoT systems.

[0005] At present, the application of common security encryption technologies on sensor nodes faces many limitations. Traditional encryption technologies usually require complex computing and storage resources. Although they can improve data security, these technologies are usually used as an additional task when executed on nodes, which inevitably increases node power consumption and affects the effect of low-power optimization. On the one hand, the complexity of encryption calculations leads to increased node power consumption, which is contrary to the goal of low-power optimization; on the other hand, the computing power and storage resources of sensor nodes are limited. Too many encryption tasks may cause excessive node load and affect the response speed to actual environmental data. How to reduce power consumption as much as possible while ensuring data security is a key problem of current technology.

[0006] To this end, this patent proposes a highly energy-efficient time-space associated distributed sensor node security anti-attack verification method, which aims to resolve the contradiction between low power consumption and high security. This method ensures the authenticity and integrity of the data by establishing a time series-neighborhood fusion security copy on the data aggregation gateway. Specifically, the gateway performs weighted processing based on the data changes of multiple sensor nodes to form a security copy that combines time series characteristics and neighborhood distribution characteristics. When the sensor data is maliciously tampered with, the security copy can assist the gateway in identifying abnormal data and correcting errors, enabling the IoT system to monitor data security in real time and reduce the impact of malicious attacks.

[0007] In addition, this method makes full use of the time series and spatial distribution information in the security replica, which can not only improve the security of data, but also optimize the working mode of the sensor node by analyzing the data change trend of the node. When the environmental changes are not obvious, the gateway can reduce the node working frequency according to the replica information, thereby reducing energy consumption; when the environment fluctuates violently, the node can increase the monitoring frequency to ensure the real-time nature of the data. Through this adaptive dynamic adjustment mechanism, the system significantly reduces the node power consumption and prolongs the battery life while ensuring data security, meeting the needs of large-scale IoT application scenarios. Summary of the invention

[0008] The purpose of the present invention is to provide a high-energy-efficiency time-space correlation distributed sensor node security anti-attack verification method, aiming at low-power consumption, high-efficiency and security enhancement of massive distributed deployment of sensor nodes. With the rapid development of Internet of Things technology, multiple sensor nodes are deployed more and more widely, forming a distributed network system composed of many sensor nodes. However, traditional sensors face two problems in real-time data collection and transmission, namely, excessive energy consumption and data security risks. These problems not only affect the continuous operation time of the equipment, but also may cause tampering or loss of data during transmission, thereby seriously affecting the reliability of the system. Therefore, there is an urgent need for a new method to reduce the energy consumption of the system and improve the overall performance of the sensor network while ensuring data security.

[0009] In order to solve the above technical problems, the technical solution adopted by the present invention is a high-energy-efficiency time-space correlation distributed sensor node security anti-attack verification method, which specifically includes the following steps:

[0010] The multi-sensor data acquisition unit collects real-time environmental data in multiple dimensions in real time. The collected data includes not only basic environmental information such as temperature, humidity and air pressure, but may also cover light intensity, noise level and other parameters that may affect the environmental state. By integrating different types of sensors, the unit can collect multi-dimensional environmental information at the same time, laying the foundation for subsequent data processing and analysis. The effectiveness of this process will directly affect the accuracy and reliability of the subsequent prediction model.

[0011] After data collection is completed, the RDMA acceleration system based on memory registration technology uses memory registration technology to offload the RDMA protocol to the DPU hardware, allowing network cards and nodes to directly read and write data, eliminating the context switching and data copy overhead of the traditional TCP / IP protocol stack. In addition, the low-power data transmission unit supports users to perform congestion control based on software programming interfaces through programmable network lossless congestion control algorithms, and is compatible with common algorithms such as DCQCN, NDP, HPCC, and LDCP, so that the system can dynamically adjust according to feedback signals such as RTT, queue depth, packet loss rate, and ECN during transmission to achieve lossless congestion control.

[0012] After receiving the data, in order to avoid the problem of deviation in the generation of the security copy of the current node due to attack, the gateway first uses the spatial neighborhood information to decide whether the current sensor node is abnormal based on the inherent change law of the physical characteristics perceived by each sensor node. The gateway receives and analyzes the data from different sensor nodes in real time, and determines its weight by calculating the spatial correlation of the data of each node. When the data of a sensor node is abnormal, the data of other sensor nodes adjacent to the node are used to calculate the weight according to the weighted algorithm to correct the data of the current node. This process not only takes into account the spatial distribution characteristics of the data, but also makes full use of the neighborhood information, so as to achieve accurate identification and effective correction of abnormal data.

[0013] Node weight coefficient formula:

[0014] Among them, α k Represents the weight coefficient of each factor, satisfying

[0015] Among them, w ij is the weight coefficient between sensor node i and neighbor node j, is the distance attenuation rate, d ij is the distance, μ is the height difference attenuation rate, h ij is the height difference, θ ij is the wind direction angle between nodes, o ij is the terrain obstacle, γ is the power attenuation rate, p i is the node power, ε is the time decay rate, t ij For the time difference.

[0016] After determining whether the current node is abnormal and processing it, the gateway uses a one-dimensional neural network (1D-CNN) and a gated recurrent unit (GRU) to analyze the time series data. By combining the feature extraction capability of 1D-CNN and the time series data processing capability of GRU, it can accurately capture the inherent change characteristics of the physical features perceived by the sensor nodes, thereby effectively predicting future data change trends and generating a time series-neighborhood fusion security copy.

[0017] Furthermore, after obtaining the safety copy, the method dynamically adjusts the sampling frequency of the sensor node based on a weighted comprehensive analysis of the changes in the first-order, second-order, and third-order derivatives of the predicted spatiotemporal sequence copies.

[0018] The first-order derivative of the replica indicates the speed of data change, reflecting the current data change trend; the second-order derivative indicates the acceleration trend of data change, reflecting the severity of the change; the third-order derivative indicates the change in the acceleration of data change, that is, the sudden change in the severity of the change. If the first-order derivative is large, the data changes more significantly at the current time point; if the second-order derivative is large, it indicates that the severity of data change has intensified, and a higher sampling frequency is required to capture subtle changes; if the third-order derivative is large, it indicates that the acceleration of the data fluctuates violently, which may indicate the occurrence of certain emergencies or extreme conditions, and the system needs to respond quickly to capture dynamic changes.

[0019] Assume that the predicted time series data is x(t), which at discrete time point t=t 1 ,t 2 ,...,t n The value is x(t i ).

[0020] Derivative of the first-order derivative of the forecast time series:

[0021] If t i The interval is a fixed step size Δt, which is simplified to:

[0022] Derivative of the second-order derivative of the forecast time series:

[0023] Derivative of the third-order derivative of the forecast time series:

[0024] Sampling rate dynamic adjustment weighted formula: S(t)=w 1 ·|v(t)| p1 +w 2 ·|a(t)| p2 +w 3·|j(t)| p3

[0025] Among them, S(t) is a comprehensive evaluation index, v(t), a(t), j(t) are the first-order, second-order, and third-order derivatives of the time series security copy, respectively, and w 1 to w 3 is the weight, which can be optimized according to the experiment and system requirements. p1, p2, and p3 are the powers of the corresponding items, which control the influence of different derivative items on the whole to optimize the overall sampling rate adjustment effect. When the derivative value is small, its weight in the comprehensive evaluation index can be further reduced by appropriately selecting the power number. (Specifically, this patent considers the first three derivative factors that have the greatest impact on its change)

[0026] Sampling frequency setting formula:

[0027] Wake-up interval formula:

[0028] Where, f(t) is the current sampling frequency, f max is the maximum sampling frequency of the sensor, to prevent the system from errors caused by excessively high sampling frequency; f min is the minimum sampling frequency of the sensor to prevent missing important information due to a large sampling interval caused by a low frequency; T 1 and T 2 are two thresholds of the comprehensive evaluation index S(t), which are used to define the range of frequency adjustment; It is a smooth adjustment parameter used to control the frequency growth rate. The larger the value, the slower the growth.

[0029] When S(t)≤T 1 When the data changes little, the sampling frequency is kept at the minimum value f min When T 1 <s(t)<T 2 When the sampling frequency is f min and f max Smoothly changing between It can be ensured that the frequency gradually increases with the increase of S(t), and the growth rate is determined by Control, Larger It can make the frequency increase smoother; when S(t)>T 1 When the data changes drastically or abnormally, the sampling frequency reaches f max , and will not continue to increase, thus avoiding the problem of infinite frequency increase.

[0030] Specifically, the adaptive difference-triggered anomaly detection unit always keeps a close watch on the difference between real-time collected data and predicted data. We innovatively incorporate an adaptive sliding window threshold mechanism into this unit to dynamically match the unique characteristics and data fluctuation patterns of different sensors. When the difference between the actual data and the predicted data exceeds the threshold dynamically set by the adaptive sliding window, the unit will quickly trigger the abnormal anti-tampering security verification mechanism. This mechanism can instantly identify abnormal fluctuations or potential tampering of data through sophisticated algorithms and efficient logical judgments, and immediately start the adaptive data integrity assurance unit.

[0031] The adaptive data integrity assurance unit includes a sophisticated exception handling mechanism. The mechanism first conducts a detailed analysis of the type and severity of the exception to determine whether the exception is caused by sensor failure, data transmission error, data processing logic defects or other potential factors. Based on the analysis results, the unit selects and executes an appropriate processing strategy, including directly discarding abnormal data, triggering sensors to re-collect data, or using mathematical methods to repair data. At the same time, the unit records the entire process of exception handling in detail, covering key details such as the exception type, the selected processing strategy, and the status of the data after processing, providing a reliable basis for subsequent in-depth data analysis and system performance optimization.

[0032] The beneficial effect of the present invention is that, through the above-mentioned high-energy-efficiency spatiotemporal correlation distributed sensor node security anti-attack verification method, the energy consumption of sensor nodes can be significantly reduced while ensuring security, and the service life of the equipment can be extended. At the same time, the model combines a one-dimensional convolutional neural network (1D-CNN) with a gated recurrent unit (GRU) to effectively extract features from multi-sensor spatiotemporal series data and improve the accuracy of anomaly detection. The introduction of an evaluation mechanism based on weighted synthesis of multi-order derivatives of predicted time series copies makes the system more flexible and robust in responding to dynamic environmental changes, and can accurately determine when to wake up the sensor for data collection. By dynamically adjusting the working state of the sensor, the system achieves an ideal balance between power consumption and security, ensuring efficient and safe operation in various IoT application scenarios. This series of innovative designs not only overcomes the bottlenecks of existing technologies, but also provides new ideas and technical directions for the sustainable development of the future smart Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is the overall architecture diagram of the high energy efficiency time-space correlation distributed sensor node security anti-attack verification method in the present invention;

[0034] Figure 2 It is a detailed flow chart of the high energy efficiency time-space correlation distributed sensor node security anti-attack verification method in the present invention;

[0035] Figure 3It is a schematic diagram of the process of the spatial neighborhood information fusion sensor data correction unit in the present invention;

[0036] Figure 4 Schematic diagram of the process of generating a unit for generating a secure copy of a time series for adaptively predicting a trend of sensor information in the present invention. DETAILED DESCRIPTION

[0037] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0038] The high-efficiency time-space correlation distributed sensor node security anti-attack verification method proposed in this invention has a system block diagram as shown in Figure 2 , wherein the method includes the following steps: the gateway first obtains real-time data from multiple sensors, and performs noise filtering and data smoothing on the collected data. The neighborhood information weighting mechanism is used to determine whether the current data is abnormal and process it. The processed data is predicted by the system, and the severity of environmental changes is determined based on the predicted time series copy, and the sampling rate of the sensor node is dynamically adjusted. After that, the system performs anomaly detection, monitors the difference between the actual data and the predicted time series security copy data in real time, and triggers an alarm and takes corresponding measures when the difference exceeds the threshold set by the sliding window. The system ensures data integrity through a multi-level adaptive security verification mechanism, and automatically initiates anti-tampering measures to deal with potential anomalies or tampering risks.

[0039] The data acquisition unit is responsible for acquiring real-time data from multiple sensors (such as temperature sensors, humidity sensors, and air pressure sensors, etc.). The unit adopts a low-power design concept and optimizes the working state of the sensor to reduce battery consumption, thereby extending the service life of the device. The data acquisition unit performs preliminary processing on the collected raw data, including noise filtering and data smoothing, to generate time series data. These processed data are then sent to the low-power data transmission unit for further data processing and transmission.

[0040] The low-power transmission unit uses memory registration technology RDMA acceleration system. The memory registration technology offloads the RDMA protocol to the DPU hardware, enabling direct data reading and writing between the network card and the application, to achieve end-to-end microsecond-level low-latency transmission, while reducing the CPU's computing overhead.

[0041] The structural diagram of the spatial neighborhood information fusion sensor data correction unit is shown in Figure 3, using the spatial conduction effect, combined with the data of the neighborhood sensor nodes, the weight of the sensor node is determined by the weighted processing formula, and the neighborhood information is used to ensure the consistency of the sensor data at the spatial level. In actual operation, the spatial neighborhood information fusion sensor data correction unit will first build a spatial data network that covers all relevant sensor nodes and their data. Subsequently, the unit will use the weighted algorithm described in the invention content section, which will assign a weight value to the data of each node based on the spatial relationship between the sensor nodes and the interdependence of the data. When the system detects that the data of a certain sensor node may be abnormal, the spatial neighborhood information fusion sensor data correction unit will immediately intervene. The unit will refer to the data of other sensor nodes adjacent to the node, as well as the weight value obtained by the weighted algorithm, to perform in-depth analysis and precise correction of the data of the current node. This correction process not only ensures the accuracy of the data, but also effectively identifies and repairs potential abnormal data.

[0042] The block diagram of the adaptive sensor information trend prediction time series security copy generation unit is shown in Figure 4 , the unit combines a one-dimensional convolutional neural network (1D-CNN) and a gated recurrent unit (GRU) to learn and analyze historical data of sensor nodes. The unit inputs the real-time sensor data after preprocessing into the 1D-CNN, and uses the convolution layer to extract local features and capture short-term patterns. The extracted features are input into the GRU, which captures long-term dependencies in the data through its gating mechanism, thereby improving prediction accuracy. Finally, the unit generates an adaptive time series security copy, which is used to predict future data trends and as a basis for dynamically adjusting the sampling rate, enhancing the reliability and security of the system.

[0043] After predicting the trend of future data changes, the gateway performs a weighted comprehensive evaluation based on the changes in the multi-order derivatives of the security copy of the predicted time series (this patent considers the first, second, and third order derivatives with greater impact of changes) and smoothly adjusts the sampling interval and target frequency of the sensor nodes. Specifically, the first-order derivative function represents the speed of data change; the second-order derivative reflects the acceleration of data change, that is, the degree of change in the speed of data change. When the value of the second-order derivative is large, it means that the trend of sensor data change is more drastic, and the gateway intelligently determines the sensor sampling rate based on this. Relatively speaking, when the value of the second-order derivative is small, it indicates that the data change is relatively slow. At this time, you can choose to reduce the sensor sampling rate to reduce power consumption; the third-order derivative function represents the change in the acceleration of data change. If the third-order derivative is large, it indicates that a mutation or anomaly has occurred, and the sampling rate should be appropriately increased. In this process, the gateway dynamically adjusts the working state of the sensor to effectively manage energy consumption and achieve a balance between energy saving and data accuracy while ensuring data integrity.

[0044] The adaptive difference-triggered anomaly detection unit monitors the difference between the actual sensor data and the safety copy of the spatiotemporal sequence in real time. The unit continuously compares the actual data with the safety copy and analyzes the deviation between the two. When the detected difference exceeds the sliding window threshold, the unit immediately triggers an alarm to prompt the system user or manager to conduct further inspection and response. At the same time, the unit records relevant abnormal data, including difference value, timestamp, sensor status and other information for subsequent analysis and auditing. This real-time monitoring mechanism ensures a rapid response to potential abnormal events, improves the reliability and safety of the system, and provides strong data support for troubleshooting.

[0045] After detecting an abnormal situation, the adaptive data integrity assurance unit automatically starts the data recovery mechanism to deal with data anomalies or tampering. The unit first identifies the type of anomaly and determines the nature of the anomaly by analyzing the data characteristics and change patterns, such as data mutation, abnormal fluctuation or time delay. According to different anomaly types, the unit flexibly adjusts the correction strategy and takes corresponding treatment measures for specific abnormal situations. For data mutation, the unit performs smoothing to reduce the impact of mutation on the overall data set; for abnormal fluctuation, the unit uses a filtering algorithm to identify and remove noise data and restore the true trend of the data; when encountering time delay, the unit adjusts the data timestamp to ensure the correctness of the data sequence. Through this multi-level detection and protection mechanism, the adaptive data integrity assurance unit can quickly respond to abnormal events and automatically recover data when necessary to ensure the integrity and reliability of the data. In addition, the unit records abnormal events and their processing for subsequent auditing and analysis, thereby continuously optimizing the verification mechanism and improving the security and stability of the system.

[0046] In practical applications, the system proposed by the present invention can be widely used in smart homes, environmental monitoring, agricultural monitoring, industrial automation and other fields. By real-time monitoring of environmental changes and timely response to emergencies, the system can improve the application level of the intelligent Internet of Things and promote the development of related technologies. Users can use the system to fully control various sensor data and make more scientific decisions and responses.

Claims

1. A high-efficiency time-space correlation distributed sensor node security anti-attack verification method, characterized in that: It includes the following units: a spatial neighborhood information fusion sensor data correction unit, an adaptive sensor information trend prediction time series security copy generation unit, a micro-power adaptive data acquisition unit, and an adaptive difference trigger anomaly detection unit; each unit works together to form a complete time series fusion endogenous security control system, which determines whether the current sensor data has been tampered with according to the change law of multi-node weighted data and corrects the erroneous data; at the same time, based on the node perception data change trend characteristics contained in the security copy, the node working mode is optimized in real time to further reduce power consumption while improving data security.

2. According to claim 1, a high-efficiency time-space correlation distributed sensor node security anti-attack verification method is characterized in that: It includes control features in both time and space. Specifically, at the time level, the inherent change law of the physical characteristics perceived by each node is used as the basis for generating subsequent security reference copies; at the space level, the neighborhood information features are added according to the deployment characteristics of the nodes surrounding each target sensor node for weighted correction. The weighted neighborhood information is based on spatial transmission information and cleverly uses the weighted correction of neighborhood sensor node data to ensure data consistency in space, effectively avoiding the problem of deviation in the generation of security copies of the current node due to attacks.

3. According to claim 1, a high-efficiency time-space correlation distributed sensor node security anti-attack verification method is characterized in that: The adaptive sensing information trend prediction time series security copy generation unit extracts the inherent change characteristics of the physical features sensed by the sensor nodes by learning historical data analysis, ensuring that the generated security copy is highly matched with the real trustworthy interval.

4. According to claim 1, a high-efficiency time-space correlation distributed sensor node security anti-attack verification method is characterized in that: The micro-power adaptive data acquisition unit uses the generated secure copy of the predicted time series to weightedly fuse the multi-order derivative change characteristics of the sensor data, and adaptively and smoothly adjusts the node sampling interval and the target frequency. While ensuring data integrity, it effectively reduces the actual required data acquisition frequency, reduces system power consumption and communication resource overhead.

5. According to claim 1, a high-efficiency time-space correlation distributed sensor node security anti-attack verification method is characterized in that: The adaptive difference-triggered anomaly detection unit can adaptively adjust the sliding window threshold according to the inherent physical characteristics of the sensed data to dynamically match the unique characteristics and data fluctuation patterns of different sensors, effectively improving the accuracy and robustness of anomaly detection.

Images