The present invention generally relates to the field of IoT and Artificial Intelligence (AI). The invention particularly relates to system and method of detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles. The system provides point-to-point monitoring of critical path between the nodes, for detecting DoS attacking nodes.

BACKGROUND OF THE INVENTION
Wormholes, denial-of-service attacks, node replication attacks, selective forwarding attacks, and other types of security assaults are common in next generation autonomous connected vehicles communication networks. VCN is a network in which many automobiles communicate with one another. Sensors, receivers, and other resources serve as a communication channel between vehicles. These kinds of resources are utilized to provide information regarding traffic and other mishaps. Security attacks such as node replication attacks, wormhole attacks, and Denial of Service (DOS) attacks, among others, disrupt this connection. Identification of this type of attack is required for proper next generation autonomous connected vehicles communication. There may be a delay in receiving information if we disregard such attacks. This delay will result in an accident, and a significant amount of time will be wasted in traffic.
DOS attack is a malicious attempt to disrupt the network and making it inaccessible to its intended users. This type of attack sends an unauthorized information again and again that crash the whole network. DOS attacks are launched by an individual, businesses, and even nation-states each with their motivation. It sends unauthorized data frequently and uses the bandwidth of the network. It hides the resources from an authorized user. This attack can present in the network layer, physical layer as well as the transport layer. DOS attacks have two types- Jamming and Tampering. In Jamming, there is an attacker who tries to stop the operation of a small network. In Tampering, attackers target the sensor nodes. A typical target for DOS includes online shopping sites, next generation next generation autonomous connected vehicles network, Online casinos, or any other online service provider business.
Several researchers have worked in the field of attack detection, VCN and DOS in last two decades. In 2003, S. Mukkamala has designed a support vector machine for DOS pattern detection and evaluate its performance using the DARPA set. This scheme can provide 90% accuracy which is better than other intrusion detection techniques. In 2006, Zhen Cao introduced a reputation-based technique called client puzzle to upgrade the protection from DOS attacks. This technique can handle the reputation value. attacked nodes have to solve the harder puzzle for getting reputation value. Hence attackers have extremely few opportunities to launch any kind of attack.
In 2011, Shi-Jinn Horng introduced a machine learning algorithm for intrusion detection system. They use the KDD Cup 1999 datasets for the evaluation of this system. This technique shows better execution in Probe attack detection. In 2011, Yin Ke-xin presents a novel powerful entropy system for the investigation of DOS. Experiment shows that this technique has a higher rate of detecting attacked nodes. In 2012, Mohit Malik used rule based technique for the detection of cyber-attack in the WSN. Malik was able to calculate the impact of 10 types of security attacks in the network. In 2012, Zhang Yi-Ying proposes a novel message observation technique (MoM) to recognize the cyber-attack. MoM uses similarity related functions to identify frequency attacks. This scheme works well not only for cyber-attack detection but also works for energy consumption.
In 2012, Manju presents a physical layer jamming identification method. In this method, she has to mark some nodes as monitor nodes and such nodes are used to monitor the jamming attack and improve system performance as well as increase packet deliver ratio. In 2014, Ahmad Iftikhar proposed a genetic algorithm for intrusion detection. They use SVM for classification in intrusion detection system. In 2014, Nikita Lyamin focused on the “Jamming” technique for the detection of false alarms in Vehicular ad-hoc networks. Their algorithm provides the more accurate result and does not show any false alarm for any jamming probability. In 2015, S. Sumitha Pandit presents an intrusion detection technique for the identification of cyber-attacks in a network. They combine the concept of Ant colony optimization with the hidden Markov model to get better performance.
In 2015, Soo-Yeon Ji introduced a method of multi-level network detection. They use NSL-KDD datasets for implementing this method. This model is 96% accurate and able to detect attack categories well. In 2016, Deepak Kshirsagar proposes an intrusion detection mechanism Local Area Network Denial for DOS detection. This system can detect DOS land. In 2016, Shital Patil proposed an immune system technique for the cyber-attack on the wireless sensor network. This technique provides a more accurate result and reduces the false alarm rate. In 2016, K. Narasimha Mallikarjunan introduced the review of DDOS attack detection strategies. They analyze various DDOS attack detection schemes and drawn conclusions about the effect of DDOS attack on the network. In 2017, Tasnuva Mahjabin present a review paper on a different kind of attack including prevention and mitigation techniques. They summarized DOS types, techniques of filtering and attack detection methods.
In 2017, Mohamed Idhammad design an artificial neural network-based DOS detection method. Here deep learning technique is used to accurately detect DOS attacks. In 2017, Chuan long Yin introduced an intrusion detection scheme with a recurrent neural network (RNN). RNN model improves the accuracy of intrusion detection systems. In 2018, Lei SU proposed a supervisory strategy for detecting the DOS attacker behavior. They analyze the performance of this technique by using attack success rate and packet reception rate. In 2019, Francisco Sales de Lima Filho presents a smart detection system for DOS attacks. The result shows that this system improve performance as compared to other techniques. In 2019, Gayathri Rajakumaran propose Gradient descent algorithm for detecting cyber security attacks. This algorithm has achieved 97% accuracy which is far better than other intrusion detection system.
In 2020, Bambang Susilo introduced a machine learning algorithm for security attack detection. Python has been used for implementing an algorithm. This algorithm provides more accurate result as compared to other techniques. In 2020, S. Sumitha designed a DNN for the DOS detection. It provides 99% Detection accuracy with less packet loss, less overhead, and better throughput as compared to other techniques. In 2020, Joao Palo proposed a novel tensor-based framework for DDOS attack detection using the concept of machine learning. This framework provides better throughput and achieves 95% accurate results. In 2020, Swathi Sambangi perform DDOS attack detection by using CICIDS 2017 dataset. This scheme has achieved 73.79% accuracy but failed to reduce training and testing error.
In 2020, Arnold Adimabua Ojugo use deep neural network for prevention of malicious node attack. Result shows 70% accuracy and reduce training as well as testing error. In 2020, Bavani K use statistical approach for DDOS attack detection in SDN. This scheme checks DDOS attack upto 500 data packets. Its accuracy rate is 97%. In 2021, Sungwoong Yeom introduced LSTM based attack detection technique. It has a 92% attack detection rate and 20% false positive rate. In 2021, Deepak Kshirsagar propose weight based reduction method for security attack detection. They use CICIDS 2017 datasets and its accuracy rate is 90%.
A number of different type of the tools and methods for replacing/changing the system for detecting Denial-of-Service (DoS) attack in a communication network are available in the prior art. For example, the following patents are provided for their supportive teachings and are all incorporated by reference: US20210034745A1 discloses a security system, and methods useful for vehicle CAN bus communication mapping and attack originator identification, comprising: a CAN Bus Monitor, (CBM), configured to monitor the CAN bus communication comprising one or more frames, to and/or from at least one Electronic Control Unit, (ECU); a characterization module in communication with the CBM, configured to generate at least one characteristic for the monitored communication from each the ECU and at least one characteristic for each communication frame; (c) a comparator unit in communication with the characterization module, configured to compare one or more the characteristics of at least one frame against characteristics of each the ECU communication in order to detect at least one anomaly; and, (d) one or more Identification module in communication with the comparator, configured to identify at least one ECU originating an attack on the CAN bus.
Another prior art document, US20200351281A1 discloses a method for identifying malicious activity that changes the integrity of data sent out from a vehicle, comprising: intercepting, by an output data monitoring agent that monitors data sent out from the vehicle to an external receiving computing unit using a communication interface in communication with a network; intercepting, by at least one sensor data monitoring agent that monitors sensor data outputted by at least one sensor associated with the vehicle; monitoring the integrity of the data sent out by the vehicle by analyzing the data collected by the output data monitoring agent with the sensor data collected by the at least one sensor data monitoring agent to identify a mismatch; and identifying an indication of malicious activity that changed the data sent out from the vehicle relative to the data sensed by the at least one sensor.
Another prior art document, EP3197730B1 discloses a vehicle correlation system for detection of at least one cyber-attack on one or more vehicles comprising a plurality of on-board communication agent modules and communicating with one another, the system comprising: first on-board communication agent modules installed within a plurality of vehicles, wherein the first on-board communication agent modules are configured to collect, process and transmit and receive first metadata to and from the correlation engine.
Another prior art document, US20200404018A1 discloses a method for detecting and countering denial of service attacks in V2X communication includes providing a vehicle with a wireless communication system including an antenna and providing a controller in communication with the wireless communication system. The method includes receiving a wireless communication, analyzing the wireless communication and determining if a first condition is satisfied. When the first condition is satisfied, the method includes calculating an angle of arrival of the wireless communication, predicting a location of a source of the wireless communication relative to the vehicle, and adjusting a gain pattern of the antenna to block reception of additional wireless communications from the source of the wireless communication.
Another prior art document, KR101807154B1 discloses a method according to an embodiment of the present invention includes: receiving at a host vehicle a plurality of messages transmitted using vehicle-to-vehicle (V2V) communication indicative of a heading angle and speed of a remote vehicle; Calculating a predicted change in the frequency of the plurality of messages received at the host vehicle based on the direction angle and speed of the remote vehicle; Measuring an actual change in the frequency of the plurality of messages received at the host vehicle due to the Doppler effect; Comparing the expected change in frequency with an actual change in the frequency; And determining that the plurality of messages are not transmitted in the remote vehicle if the difference between the expected change in frequency and the actual change in frequency exceeds a predetermined frequency change threshold value.
However, above mentioned references and many other similar references has one or more of the following shortcomings: (a) Unable to detect DoS attack which slow down the process, damage network resources, generate a lot of fake signals, hangs the complete system, generate malicious packets, and increase the network load; (b) Complex process; (c) More time consuming; (d) Less accuracy; (e) Costly; and (f) Point to point critical path monitoring is not available.
The present application addresses the above-mentioned concerns and shortcomings (and other similar concerns/shortcomings) with regard to detect Denial-of-Service (DoS) attack in a communication network.
There remains a constant need in society for a continuous flow of new and innovative novelty of a system to detecting Denial-of-Service (DoS) attack in a communication network. It is in this context, that the subject invention is useful, not only to provide cheap and easy to operate/use but to provide system for detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles with integration of IoT and AI technology.

SUMMARY OF THE INVENTION:
In the view of the foregoing disadvantages inherent in the known types of technologies for detecting Denial-of-Service (DoS) attack now present in the prior art, the present invention provides an improved system 100 detecting Denial-of-Service (DoS) attack in a communication network. As such, the general purpose of the present invention, which will be described subsequently in greater detail, is to provide a new and improved system 100 detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles, which has all the advantages of the prior art and none of the disadvantages.
It is object of the invention is to provide a system 100 for detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles, said system 100 comprising: a communication network 101, a plurality of sensors installed in each of the plurality of nodes 102, a Support Vector Machine (SVM) 103, a cloud server 104, a memory 105 communicatively coupled to the processor 106. The memory 105 stores processor 106 instructions, which, on execution, causes the processor to detect DoS attack in said communication network based on at least one of sensor reading, a message size, or a network specification. It should be noted that the plurality of nodes 102 are installed in each of the vehicles in said communication network 101.
It is another object of the present invention is to provide the method of detecting Denial-of-Service (DoS) attack in a communication network 101 comprising: pre-processing, by the system 100, to identify a critical path between each of the plurality of nodes 102 in said communication network 101 based on said network specification; training, by the system 100, said Support Vector Machine (SVM) 103 through each of said critical path and said network specification of each of the plurality of nodes 102 in said communication network 101; point to point scanning of said critical path between each of the plurality of nodes 102 in said communication network 101; detecting, by said SVM 103, a DoS attacking nodes of the plurality of nodes 102 in said communication network 101 based on at least one of sensor reading, a message size, or a network specification, wherein said message size is identified based on data provided by a DoS attacker; and removing, by said system 100, said DoS attacking nodes from said communication network 101 to provide smooth working of vehicular communication.
Yet another object of the present invention is that the network specification comprises at least one of number of nodes, area length, area width, sensor data, message size, dimensions, percentage of attacked nodes, maximum number of rounds, or the like.
Yet another object of the present invention is to provide a SVM 103 which is used to classify said plurality of nodes in classes, out of which one class comprises said DoS attacking nodes and second class comprises remaining nodes of the plurality of nodes 102.
Yet another object of the present invention is that the SVM 103 calculates training error and testing error.
Yet another object of the present invention is that the sensor reading, message size, critical path, and network specification are stored in cloud server 104.
Yet another object of the present invention is that the system 100 provides increased accuracy, throughput, faster response, and less elapsed time in said communication network 101 by removing said DoS attacking nodes.
In this respect, before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not limited in its application to the details of construction and to the arrangements of the components set forth in the following description or illustrated in the drawings. The invention is capable of other embodiments and of being practiced and carried out in various ways. 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.
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 had to the accompanying drawings and descriptive matter in which there are illustrated preferred embodiments of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
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:
Fig. 1 illustrates a system for detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles, according to an embodiment herein.
Fig. 2 depicts a flow chart of working of system for detecting Denial-of-Service (DoS) attack in a communication network, according to an embodiment herein.
Fig. 3 depicts a graph of Normal nodes and attacked nodes in next generation autonomous connected vehicles communication network, according to an embodiment herein.
Fig. 4 depicts an exemplary method of detecting Denial-of-Service (DoS) attack in a communication network, according to an embodiment herein.

DETAILED DESCRIPTION OF THE INVENTION
In the following detailed description, reference is made to the accompanying drawings which form a part hereof, and in which is shown by way of illustration specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention, and it is to be understood that the embodiments may be combined, or that other embodiments may be utilized and that structural and logical changes may be made without departing from the spirit and scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined by the appended claims and their equivalents.
References will now be made in detail to the exemplary embodiment of the present disclosure. Before describing the detailed embodiments that are in accordance with the present disclosure, it should be observed that the embodiments reside primarily in combinations arrangement of the system according to an embodiment herein and as exemplified in FIG. 1 – FIG. 4.
In the following description, for the purpose of explanation, numerous specific details are set forth in order to provide a thorough understanding of the arrangement of the system according to an embodiment herein. It will be apparent, however, to one skilled in the art, that the present embodiment can be practiced without these specific details. In other instances, structures are shown in block diagram form only in order to avoid obscuring the present invention.
Fig. 1 illustrates a system 100 for detecting Denial-of-Service (DoS) attack in a communication network of next generation autonomous connected vehicles, according to an embodiment herein. The system 100 includes a communication network 101, a plurality of sensors installed in each of the plurality of nodes 102, a Support Vector Machine (SVM) 103, a cloud server 104, a memory 105 communicatively coupled to the processor 106.
The system 100 uses the SVM to implement a Point-to-Point Critical Path Monitoring (P2PCPM) based Denial of Service (DOS) Attack detection technique for next generation Vehicular Communication Network (VCN) resource management. The best thing about P2PCPM is that it removes attacked nodes from the network and speeds up vehicle communication. In terms of efficiency, accuracy, and rate of attack detection, it outperforms other security detection algorithms. The entire monitoring system is created and tested using MATLAB software. The design, execution, and simulation are completed, and the results are tabulated in a methodical manner.
While implementing the system 100, results indicate a 100% attack detection accuracy as well as a two percent reduction in training/testing error. Finally, the experimental findings show that this strategy works well up to 1000 nodes, which is the current implementation's constraint, and that in the future, the accuracy test may be performed for limitless nodes and massive data detection in VCN using similar or other detection techniques.
Fig. 2 depicts a flow chart 200 of working of system 100 for detecting Denial-of-Service (DoS) attack in a communication network, according to an embodiment herein. The system 100 use P2PCPM based DOS attack detection for vehicular communication network resource management.
The system 100 may detect DOS attack in a next generation autonomous connected vehicles communication network using a support vector machine (SVM). The goal is to remove the attacked vehicles which creates problem in communication between vehicles. The next generation autonomous connected vehicles communication network Resource Management contains thousands of sensors of nodes. This node is prepared with various sensing devices. Their processing speed, storage capacity, and communication bandwidth is limited. It should be noted that the Message Size was transmitted by the attackers whereas the sensor data that are taken from vehicles.
In the whole process from next generation vehicular communication network generation to attack detection, in every round, the system 100 may detect the attacked nodes and speed up the communication process between automobiles. At step 201, the system 100 may receive network specification of the vehicular communication network to set up an environment for network resource management. Further at step 202, the system 100 may preprocess the network specifications to identify critical path of least resistance. It should be noted that the network specifications may include number of nodes, Area length, Area Width, Sensor Data, Message size, Dimensions, percentage of attacked nodes, maximum number of rounds, or the like.
Further at step 203, the system 100 may start simulation on the setup environment based on received data from the permanent database at step 204. Intel i3 processor with 4 GB RAM support this simulation. It should be noted that, MATLAB 2018 have best features which are used for implementation of this system 100. Further at step 205, the system 100 may train the SVM to detect Denial-of-Service (DoS) attack in a communication network 101. After generating a next generation autonomous connected vehicles communication network, a training set using a support vector machine will be generated and the SVM is tested on data very similar to real sensing data to evaluate the ability of this SVM to detect attacked nodes and calculate both training and testing error.
The SVM is an algorithm that learns by example to assign tags to object. For example- the SVM can learn to recognize handwritten digits by investigating the scanned images of handwritten zeroes. In the system 100, the SVM recognize DOS attack by sensor reading and message size. It is very effective in high dimensional space. It works well for a small or large datasets. Its separate data into two classes. It should be noted that the SVM divide data into normal node as well as attacked nodes. In this stage, a training set will be generated which includes sensor reading, message size and status of nodes.
Further at step 206, the system 100 may scan all the plurality of nodes in the communication network or DOS attack detection. Further, when the system 100 may detect a DOS attacking node at step 207 then the system 100 may remove the malicious node from the communication network at step 208. But, when the system 100 may not detect a DOS attacking node at step 207 then the system 100 may work smoothly for vehicular communication at step 208.
Fig. 3 depicts an exemplary graph 300 of Normal nodes and attacked nodes in next generation autonomous connected vehicles communication network, according to an embodiment herein. After Detecting attacked nodes speed of communication between vehicles will be increasing. Hence, the system 100 may remove the attacked nodes and the communication process between other vehicles increasing continuously. Here two different scenarios are the normal node and attacked node. In a normal node, communication between nodes will continue otherwise in DOS attacked node, the message passing through that node automatically stops during the simulation of n no of nodes.
By the way of an example there are there are 6 bad nodes whose sensor data is above 25 and message size is 500. Then,
Accuracy= (Attacked nodes detected)/(Attacked nodes present)*100= 6*100/6=100%
False Positive Rate (FPR)= (Number of misclassified DOS attacked nodes*100)/(Actually Attacked Nodes)= 1*100/6=16%. And,
Elapsed Time= the time taken by the software to detect attacked nodes= 128 Sec.

Hence, the system 100 works for more than 1000 nodes and provide 100% accurate result. It takes only 132 seconds to train the model and 128 seconds to test the model. Its false positive rate is 16% and reduce training as well as testing error upto 2%. A DOS attack on up to 1000 vehicle nodes. In this scenario, the system 100 considered a DOS assault on up to 100 nodes, with 6 nodes being attacked.
After altering network specifications, the system 100 can verify attacked nodes again and again. The detection of DOS assaults has a 100% success rate. The model requires 132 seconds to train and 128 seconds to test. The communication process runs smoothly when the attacked nodes have been detected. In comparison to other security detection models, this scheme performs admirably. The results of the experiments show that this methodology provides more accurate findings for the next generation of autonomous connected vehicles communication networks. This approach may also be used to detect other types of attacks, such as wormholes and node replication assaults.
Fig. 4 depicts an exemplary method 400 of detecting Denial-of-Service (DoS) attack in a communication network, according to an embodiment herein. At step 401, the system 100 may pre-process, by the system 100, to identify a critical path between each of the plurality of nodes 102 in said communication network 101 based on said network specification. Further at step 402, the system 100 may training, by the system 100, said Support Vector Machine (SVM) 103 through each of said critical path and said network specification of each of the plurality of nodes 102 in said communication network 101.
Further at step 403, the system 100 may point to point scan the critical path between each of the plurality of nodes 102 in said communication network 101. Further at step 404, the system 100 may detect, by said SVM 103, a DoS attacking nodes of the plurality of nodes 102 in said communication network 101 based on at least one of sensor reading, a message size, or a network specification. It should be noted that the message size is identified based on data provided by a DoS attacker. Further at step 405, the system 100 may remove, by said system 100, said DoS attacking nodes from said communication network 101 to provide smooth working of vehicular communication.
Hence, the system 100 can generate a point-to-point critical path monitoring based network to identify high performance network nodes with least resistance of adaptive environment network data packets. Moreover, the system 100 identifies DOS attacked nodes from the next generation autonomous connected vehicles communication network. Moreover, the system 100 remove the DOS attacked nodes from the network and preprocess to identify high performance network nodes This process continue until all attacked nodes are not detected. After removing DOS attacked nodes from the network, next generation autonomous connected vehicles communication process work smoothly.
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.
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.
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.

(6) CLAIMS
We / I Claimed:
1. A system 100 for detecting Denial-of-Service (DoS) attack in a
communication network of next generation autonomous connected
vehicles, said system 100 comprising:
A communication network 101,
a plurality of sensors installed in each of the plurality of nodes 102,
a Support Vector Machine (SVM) 103,
a cloud server 104,
a memory 105 communicatively coupled to the processor 106;
wherein the memory 105 stores processor 106 instructions, which, on
execution, causes the processor to detect DoS attack in said
communication network based on at least one of sensor reading, a
message size, or a network specification; and
wherein said plurality of nodes 102 are installed in each of the
vehicles in said communication network 101.
2. The system 100 as claimed in claim 1, wherein method of
detecting Denial-of-Service (DoS) attack in a communication
network 101 comprising:
pre-processing, by the system 100, to identify a critical path
between each of the plurality of nodes 102 in said communication
network 101 based on said network specification;
training, by the system 100, said Support Vector Machine
(SVM) 103 through each of said critical path and said network
specification of each of the plurality of nodes 102 in said
communication network 101;
point to point scanning of said critical path between each of
the plurality of nodes 102 in said communication network 101;
detecting, by said SVM 103, a DoS attacking nodes of the
plurality of nodes 102 in said communication network 101 based on
at least one of sensor reading, a message size, or a network
19
specification, wherein said message size is identified based on data
provided by a DoS attacker; and
removing, by said system 100, said DoS attacking nodes from
said communication network 101 to provide smooth working of
vehicular communication.
3. The system 100 as claimed in claim 1, wherein said network
specification comprises at least one of number of nodes, area length,
area width, sensor data, message size, dimensions, percentage of
attacked nodes, maximum number of rounds, or the like.
4. The system 100 as claimed in claim 1, wherein said SVM 103
classify said plurality of nodes in classes, wherein one class
comprises said DoS attacking nodes and second class comprises
remaining nodes of the plurality of nodes 102.
5. The system 100 as claimed in claim 1, wherein said SVM 103
calculates training error and testing error.
6. The system 100 as claimed in claim 1, wherein each of said sensor
reading, message size, critical path, and network specification are
stored in cloud server 104.
7. The system 100 as claimed in claim 1, wherein said system 100
provides increased accuracy, throughput, faster response, and less
elapsed time in said communication network 101 by removing said
DoS attacking nodes.