Description:[001] The present disclosure, in general, relates to the technical field of cyber security and privacy. More specifically, the present invention relates to an Enhanced Cyber-Physical System for Source Location Privacy based on an Active Learning-based Ensemble Classifier in Wireless Sensor Network.
BACKGROUND OF THE INVENTION
[002] The following description provides the information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[003] In modern wireless sensor networks (WSNs), sensors are often deployed over large geographical areas to collect data for various applications, including environmental monitoring, healthcare, military surveillance, and smart cities. These networks are typically composed of distributed sensor nodes that communicate wirelessly, transmitting valuable data to a central processing system for analysis. However, one of the major concerns in WSNs is protecting the privacy of the source location of data, as malicious adversaries could potentially intercept wireless communications and infer the locations of sensitive data sources. This poses serious privacy risks, such as unauthorized tracking, location-based attacks, and leakage of sensitive information. In the context of modern wireless sensor networks (WSNs), the protection of sensitive data has become an increasingly critical concern, especially when it comes to maintaining the privacy of the source location.
[004] WSNs consist of numerous sensor nodes deployed over a geographical area, typically collecting environmental data, monitoring physical conditions, or tracking objects. These sensor nodes transmit data to a central server or sink node, where the information is processed and analysed. While these systems are highly effective in a variety of applications such as environmental monitoring, military surveillance, healthcare, and smart cities, the privacy of the data particularly regarding the physical location of the data source – is a significant challenge. The issue of source location privacy arises because adversaries, through eavesdropping on wireless communication, can potentially infer the geographical location of the data source. This could lead to various security risks, such as unauthorized tracking of individuals or tampering with the data or sensor nodes.
[005] Therefore, preserving the anonymity of sensor nodes' locations is vital in preventing malicious actors from gaining sensitive information that could compromise the integrity and security of the system. One approach to achieving source location privacy is through the use of cryptographic techniques, but these methods are computationally expensive and may introduce delays, which are undesirable in real-time systems. Alternatively, obfuscation techniques, which involve altering the communication paths and routing of sensor data, can reduce the precision with which an adversary can pinpoint the source location. However, these techniques often come at the cost of network efficiency and data accuracy.
[006] Accordingly, to overcome the prior art limitations based on aforesaid facts. The present invention provides an Enhanced Cyber-Physical System for Source Location Privacy based on Active Learning-based Ensemble Classifier in Wireless Sensor Network. Therefore, it would be useful and desirable to have a system, method and apparatus to meet the above-mentioned needs.

SUMMARY OF THE PRESENT INVENTION
[007] The active learning and ensemble classifiers have emerged as powerful tools to improve privacy-preserving techniques while minimizing resource consumption. Active learning, a subset of machine learning, enables a system to selectively choose the most informative data to improve the accuracy of models with fewer labelled instances. By using active learning, the system can adapt and learn more effectively with minimal interaction from human users or manual labelling.
[008] An ensemble classifier, which combines multiple machine learning models to make decisions, can improve the accuracy and robustness of source location privacy techniques by leveraging the strengths of multiple classifiers to reduce the likelihood of being compromised by adversarial attacks. In the context of a cyber-physical system (CPS) a system that integrates physical processes with computational and communication capabilities these techniques can be used to enhance both the security and efficiency of location privacy strategies in WSNs. An ensemble classifier-based active learning approach can work by dynamically identifying and evaluating data from sensor nodes to ensure that source locations are obfuscated effectively.
[009] The classifier system can intelligently adjust its privacy-preserving strategies based on the evolving network conditions and detected threats, improving the system's ability to protect sensitive location data while maintaining the overall performance of the network. Protecting the location data of sensors monitoring traffic, air quality, and public safety. Preserving the privacy of patients in medical monitoring systems where wearable sensors may report sensitive information.
[010] Securing location information of sensors tracking natural resources, weather patterns, or wildlife in sensitive ecosystems. Preventing adversaries from tracking the location of military assets or personnel in battlefield environments. Overall, the present system not only enhances the privacy and security of source location in wireless sensor networks but also ensures that privacy-preserving techniques are implemented with minimal impact on network efficiency, making it a highly practical solution for a wide range of cyber-physical applications.
[011] In this respect, before explaining at least one object of the invention in detail, it is to be understood that the invention is not limited in its application to the details of the set of rules and to the arrangements of the various models set forth in the following description or illustrated in the drawings. The invention is capable of other objects and of being practiced and carried out in various ways, according to the need of that industry. Also, it is to be understood that the phraseology and terminology employed herein are for the purpose of description and should not be regarded as limiting.
[012] These together with other objects of the invention, along with the various features of novelty which characterize the invention, are pointed out with particularity in the disclosure. For a better understanding of the invention, its operating advantages and the specific objects attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated preferred embodiments of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
[013] The invention will be better understood and objects other than those set forth above will become apparent when consideration is given to the following detailed description thereof. Such description makes reference to the annexed drawings wherein:
[014] FIG. 1, illustrates a flowchart of an Enhanced Cyber-Physical System for Source Location Privacy based on Active Learning-based Ensemble Classifier in Wireless Sensor Network, in accordance with an embodiment of the present invention.
[015] FIG. 2, depicts a block diagram of an Enhanced Cyber-Physical System for Source Location Privacy based on Active Learning-based Ensemble Classifier in Wireless Sensor Network, in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION OF THE INVENTION
[016] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claims. As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein is solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles and the like is included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all of these matters form part of the prior art base or are common general knowledge in the field relevant to the present invention.
[017] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
[018] The present invention is described hereinafter by various embodiments with reference to the accompanying drawings, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, a number of materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[019] The present invention relates to the present invention relates to an enhanced Cyber-Physical System for Source Location Privacy (CPS-LP) is introduced, leveraging an Active Learning-based Ensemble Classifier. This system employs advanced machine learning techniques to intelligently classify and obscure the source location of sensor data while maintaining network performance, efficiency, and robustness against various attacks. By integrating active learning and ensemble classifiers, the proposed system adapts dynamically to network conditions and adversarial threats, ensuring that location privacy is preserved in a computationally efficient manner.
[020] In accordance with an embodiment of the present invention, the proposed CPS-LP system consists of several key components such as Wireless Sensor Network (WSN), the WSN is made up of distributed sensor nodes that are responsible for sensing and transmitting data about physical phenomena, such as temperature, humidity, or air quality. These nodes communicate wirelessly and may be deployed over large areas in potentially hostile environments. Each sensor node generates data and transmits it to a sink node or central processing unit. The data transmitted may include time-stamped readings, sensor identifiers, and location coordinates, all of which could reveal sensitive information if intercepted.
[021] In accordance with another embodiment of the present invention, the active learning module continuously interacts with the WSN to determine which data points are most valuable for learning and classification. Rather than requiring a fully labelled dataset for training, active learning enables the system to selectively query the most uncertain or high-risk data points for labelling. This reduces the amount of labelled data required for model training and helps the system adapt quickly to changes in the network and adversarial behavior. In the context of source location privacy, active learning is used to determine the most effective strategies for obfuscating source location information in real-time, dynamically adjusting the system's privacy-preserving measures based on the evolving conditions of the WSN.
[022] In accordance with another embodiment of the present invention, the ensemble classifier combines multiple individual machine learning models to improve the overall accuracy and robustness of the privacy-preserving mechanism. Each classifier in the ensemble may specialize in different aspects of the data, such as detecting unusual communication patterns, identifying potential attacks, or predicting the most effective privacy strategy for a given sensor node. By aggregating the outputs of multiple classifiers, the system benefits from the "wisdom of crowds" effect, where diverse models collaborate to achieve a more accurate and stable decision-making process. This approach enhances the ability of the system to correctly classify and obscure source locations while minimizing errors or failures.
[023] In accordance with another embodiment of the present invention, the common techniques used for ensemble classifiers include Random Forest, Boosting (e.g., AdaBoost), and Bagging (e.g., Bootstrap Aggregating), which allow the system to aggregate the predictions from multiple decision trees or models. The primary objective of the CPS-LP system is to obfuscate the source location of sensor data to preserve privacy. The system employs several privacy-preserving techniques, including routing obfuscation, dummy traffic generation, and location perturbation. The technique involves modifying the communication paths of sensor data to prevent attackers from easily inferring the location of the data source. By dynamically selecting routing paths, the system ensures that data does not travel along predictable routes.
[024] In accordance with another embodiment of the present invention, the Dummy traffic can be added to the network to further obfuscate the actual communication patterns, making it more difficult for attackers to distinguish between real and fake traffic. The system can apply controlled randomization to the reported location data, ensuring that the actual location of the sensor node is obfuscated within a defined radius. This technique strikes a balance between privacy and the accuracy of the transmitted data. The ensemble classifier also plays a critical role in detecting potential security threats or attacks that could compromise the source location privacy. For example, attackers may attempt to launch localization attacks where they triangulate the position of the data source based on signal strength or timing information. The classifier identifies abnormal communication patterns indicative of such attacks and triggers countermeasures such as adjusting routing paths or increasing the level of obfuscation for compromised nodes. The system also leverages active learning to improve its ability to detect and respond to new types of attacks.
[025] Furthermore, the Enhanced Cyber-Physical System for Source Location Privacy based on Active Learning-based Ensemble Classifiers represents a significant advancement in the field of privacy-preserving wireless sensor networks. By combining the power of active learning, ensemble machine learning techniques, and privacy-preserving strategies, the system offers a highly effective and adaptable solution for ensuring the privacy of sensor node locations while maintaining the efficiency and scalability of large-scale networks. This approach not only protects sensitive data but also enhances the overall security and robustness of the system, making it suitable for a wide range of applications where location privacy is paramount.
[026] It is to be understood that the above description is intended to be illustrative, and not restrictive. For example, the above-discussed embodiments may be used in combination with each other. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description.
[027] The benefits and advantages which may be provided by the present invention have been described above with regard to specific embodiments. These benefits and advantages, and any elements or limitations that may cause them to occur or to become more pronounced are not to be construed as critical, required, or essential features of any or all of the embodiments.
[028] While the present invention has been described with reference to particular embodiments, it should be understood that the embodiments are illustrative and that the scope of the invention is not limited to these embodiments. Many variations, modifications, additions and improvements to the embodiments described above are possible. It is contemplated that these variations, modifications, additions and improvements fall within the scope of the invention.
, Claims:1. A cyber-physical system for source location privacy in a wireless sensor network (WSN), comprising:
a. A plurality of wireless sensor nodes deployed in a monitored area, each sensor node configured to collect and transmit data packets;
b. A source node that generates event-based data packets for transmission through the WSN;
c. A privacy-preserving routing mechanism that obfuscates the actual source location using active learning-based ensemble classification;
d. An ensemble classifier framework comprising multiple machine learning models trained to distinguish routing anomalies and optimize the obfuscation of the source location;
e. An active learning module that selectively queries sensor nodes to update the ensemble classifier dynamically based on real-time network conditions; and
f. A cyber-physical security module that detects and mitigates adversarial attacks targeting the source location privacy mechanism.

2. The system as claimed in claim 1, wherein the ensemble classifier comprises a combination of decision trees, support vector machines (SVMs), and deep learning models to improve classification accuracy.

3. The system as claimed in claim 1, wherein the privacy-preserving routing mechanism employs a combination of phantom routing, random walk-based routing, and controlled random delay mechanisms to obscure the source location from adversaries.

4. The system as claimed in claim 1, further comprising an adaptive noise injection module that perturbs routing paths using synthetic noise packets to mislead eavesdroppers attempting to trace back to the source node.

5. A method for enhancing source location privacy in a wireless sensor network using an active learning-based ensemble classifier, comprising:
a. Collecting network traffic data from multiple sensor nodes;
b. Training an initial ensemble classifier using labeled routing data;
c. Deploying the classifier within the WSN to identify routing anomalies and improve source location obfuscation;
d. Dynamically updating the classifier using active learning to improve classification efficiency with minimal manual intervention;
e. Implementing an obfuscation strategy that integrates random routing, artificial noise packets, and controlled delays; and
f. Detecting and responding to adversarial attacks through a cyber-physical security module.