Machine Learning Techniques to Combat Phishing Attacks

By: Jampula Navaneeth1

1Vel Tech University, Chennai, India

2International Center for AI and Cyber Security Research and Innovations, Asia University, Taiwan, Email: navaneethjampula@gmail.com

Abstract

In this paper we are going to see how machine learning techniques will combat phishing attacks. In the area of cyberattacks, phishing attacks are one of the fast-growing fraudulent crimes. Basically phishing is a trap to get someone personal data just by clicking URL links, emails and websites. To prevent this we are going to use machine learning techniques. There are many applications in detecting the phishing attacks, but only few of them can only compared to combat phishing attacks. In this study we are going to see various machine learning techniques and there uses so that it can be easy to combat phishing attacks. This short article may help to many researchers, students and knowledge seekers on how the machine learning techniques are utilized and there importances.

Keywords: Machine Learning, Phishing attacks, Techniques

Introduction

Machine Learning is the sub branch of artificial intelligence. ML is mainly designed to match the human brains by learning from the surroundings. The techniques involves in various fields such as pattern recognition, computer vision, finance, entertainment and in medical applications [1].

Phishers basically trap people by sending false emails, messages which looks like the genuine information, From there they will gain trust from the people and then they slowly start tracking the personal data, bank details of the trustworthy persons [2]. There involve various types of phishing attacks which may lead to various trapping crimes. To prevent these types of attacks machine learning techniques are utilized in various ways.

Techniques

A recent study emphasized the impact of a stacking model on the detection of bona fide websites. The model gained higher accuracy in comparison to many other machine learning models on several performance indicators. They examined the machine learning techniques applied to identify SSD technology from the detection angle of positive and negative rates. New meta-learning methods such as Phishing Classification, which contributed the key features of data to result in better fashion, were discovered to be the most suitable machine learning algorithms for anti-phishing. A couple of techniques like numeric representation and URL metadata for website legitimacy evaluation had been experimented with Random Forest and SVM models which outperformed all others in the task [3].

To identify the malicious URLs, the proactive strategy was used based on lexical analysis. It was made possible through the use of machine learning techniques to classify the various forms fields of URLs. Phishing detection by PCA (Principal Component Analysis) and the Random Forest algorithm were the fuels of those fireworks [4]. The principal component analysis method helped identify principal components from the data stream as evidenced by numbers, and the website classification method based on the use of Random Forest algorithm ensured a satisfactory positive count of the emails with phishing attack scope (almost 96%). Considering that this methodology does not require any smart gadgets or equipment, its flexibility and scalability are self-evident. [2].

Figure 1 : Machine Learning Classifications

Challenges

It is a challenging work for the successful implementation of machine learning techniques to detect phishing in a secure way. Though traditional machine learning techniques are sufficient in the case of detection rates, more complex deep learning techniques are able to obtain better accuracy. Logistic regression is one of the predictive models doing well in classification but it has several drawbacks when the feature is repeated, or two-way combinations or outliers are present. An increasingly used method to combat these attacks is machine learning which is popular for its capability of detection. Students in a phishing practice and spam class are more and more likely to employ machine learning as a detection tool. The RF technique has also been demonstrated to be more efficient than other methods, but the choice of the feature regarding the prediction task are still challenging and prevailing problems that can be solved by retraining the classifier frequently [3].

Conclusion

In a conclusion, machine learning techniques have demonstrated high efficacy in the fight against phishing through the use of complex algorithms and feature extraction methodologies. These approaches enable precise classification of URLs, e-mails and other digital contents leading to improved detection and prevention of phishing attacks. Furthermore, principal component analysis integrates refine this process enhancing robustness towards changing phishing methods [5]. For continuous protection of cyber security, machine learning models must be developed constantly as e-business expands. ML stays one step ahead by being inventive yet adaptive thereby having dynamic proactive defense against ever-present menace like phishing attacks

Reference

  1. I. El Naqa and M. J. Murphy, “What Is Machine Learning?,” in Machine Learning in Radiation Oncology: Theory and Applications, I. El Naqa, R. Li, and M. J. Murphy, Eds., Cham: Springer International Publishing, 2015, pp. 3–11. doi: 10.1007/978-3-319-18305-3_1.
  2. M. N. Alam, D. Sarma, F. F. Lima, I. Saha, R.-E.- Ulfath, and S. Hossain, “Phishing Attacks Detection using Machine Learning Approach,” in 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Aug. 2020, pp. 1173–1179. doi: 10.1109/ICSSIT48917.2020.9214225.
  3. A. Odeh, I. Keshta, and E. Abdelfattah, “Machine LearningTechniquesfor Detection of Website Phishing: A Review for Promises and Challenges,” in 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), Jan. 2021, pp. 0813–0818. doi: 10.1109/CCWC51732.2021.9375997.
  4. S. Manikandan, M. Rahaman, and Y.-L. Song, “Active Authentication Protocol for IoV Environment with Distributed Servers,” Computers, Materials & Continua, vol. 73, no. 3, pp. 5789–5808, 2022, doi: 10.32604/cmc.2022.031490.
  5. M. Rahaman, F. Tabassum, V. Arya, and R. Bansal, “Secure and sustainable food processing supply chain framework based on Hyperledger Fabric technology,” Cyber Security and Applications, vol. 2, p. 100045, Jan. 2024, doi: 10.1016/j.csa.2024.100045.
  6. Gupta, B. B., Gaurav, A., & Panigrahi, P. K. (2023). Analysis of retail sector research evolution and trends during COVID-19. Technological Forecasting and Social Change, 194, 122671.
  7. Aldweesh, A., Alauthman, M., Al Khaldy, M., Ishtaiwi, A., Al-Qerem, A., Almoman, A., & Gupta, B. B. (2023). The meta-fusion: A cloud-integrated study on blockchain technology enabling secure and efficient virtual worlds. International Journal of Cloud Applications and Computing (IJCAC), 13(1), 1-24.
  8. M. Casillo, F. Colace, B. B. Gupta, A. Lorusso, F. Marongiu and D. Santaniello, “Blockchain and NFT: a novel approach to support BIM and Architectural Design,” 2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Sakheer, Bahrain, 2022, pp. 616-620, doi: 10.1109/3ICT56508.2022.9990815.

Cite As

Navaneeth J. (2024) Machine Learning Techniques to Combat Phishing Attacks, Insights2Techinfo, pp.1

78350cookie-checkMachine Learning Techniques to Combat Phishing Attacks
Share this:

Leave a Reply

Your email address will not be published.