Manuscript Number : SHISRRJ247251

Cyber Hacking Breaches Prediction Using Machine Learning

Authors(2) :-T. Rajasekhar, Mukku Keerthna

The combination of physical processes, computational resources, and communication capabilities has driven major advancements in many dynamic applications of cyber-physical systems (cps). Cyberattacks, however, pose a serious risk to these systems. Cyber-attacks are smart and covert, in contrast to cyber-physical system defects that arise accidentally. Certain attacks, referred to as deception attacks, introduce erroneous data into the system by manipulating sensors or controllers, or by breaching cyber components and contaminating or introducing false information. The system may experience performance issues or become completely disabled if it is not aware that these attacks are occurring. Consequently, in order to recognize these kinds of assaults in these systems, algorithms must be modified. These systems generate large amounts of different, rapidly created data, so that's essential to use machine learning techniques to identify hidden trends and facilitate data analysis and review. This study models the CPS as a network of moving agents that work in union with among themselves. The model recognizes a leader agent and gives commands to the other agents in the network. The study's suggested approach makes use of deep neural network architecture for the detection stage, which should alert the system to the attack's presence in the early stages. Researchers have investigated isolating the misbehaving agent in the leader-follower system utilizing robust control methods within the network. In the proposed control strategy, the phase of assault detection is executed by a deep neural network, after The control system employs a reputation algorithm to identify and separate the agent exhibiting misconduct. Through experimental study, we can see that deep learning algorithms are able to detect assaults at a better performance level.

Authors and Affiliations

T. Rajasekhar
Assistant Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India
Mukku Keerthna
Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India

Decision Tree, Random Forest, CatBoost, Adaboost, Logistic Regression, KNN, SVC

  1. Kwon, Cheolhyeon, Weiyi Liu, and Inseok Hwang. ”Security analysis for cyber-physical systems against stealthy deception attacks.” In 2013 American control conference, IEEE (2013): 3344-3349
  2. Pajic, Miroslav, James Weimer, Nicola Bezzo, Oleg Sokolsky, George J. Pappas, and Insup Lee. ”Design and implementation of attack-resilient cyberphysical systems: With a focus on attack-resilient state estimators.” IEEE Control Systems Magazine 37, no. 2 (2017): 66-81.
  3. Sheng, Long, Ya-Jun Pan, and Xiang Gong. ”Consensus formation control for a class of networked multiple mobile robot systems.” Journal of Control Science and Engineering 2012 (2012).
  4. Zeng, Wente, and Mo-Yuen Chow. “Resilientdistributed control in the presence of misbehaving agents in networked control systems.” IEEE transactions on cybernetics 44, no. 11 (2014): 2038-2049.
  5. Sun, Hongtao, Chen Peng , Taicheng Yang, Hao Zhang, and Wangli He. “Resilient control of networked control systems with stochastic denial of service attacks.” Neuro computing 270 (2017): 170-177.

Publication Details

Published in : Volume 7 | Issue 2 | March-April 2024
Date of Publication : 2024-04-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 173-179
Manuscript Number : SHISRRJ247251
Publisher : Shauryam Research Institute

ISSN : 2581-6306

Cite This Article :

T. Rajasekhar, Mukku Keerthna, "Cyber Hacking Breaches Prediction Using Machine Learning", Shodhshauryam, International Scientific Refereed Research Journal (SHISRRJ), ISSN : 2581-6306, Volume 7, Issue 2, pp.173-179, March-April.2024
URL : https://shisrrj.com/SHISRRJ247251

Article Preview