Application of the Artificial Intelligence Tools and Techniques in the Efficacious Detection of Phishing Unique Resource Locator (URL)

Somya Panchal

Vol. 6, Jan-Dec 2020

Page Number: 183 - 185

Abstract:

Phishing is one of the most common methods for launching cyberattacks. Recent statistics indicate that 97% of users could not recognize sophisticated phishing emails. With the monthly creation of over 1.5 million new websites, legacy blocklists and rule-based filters can no longer mitigate the increasing risks and sophistication of phishing. Phishing can send different toxic payloads that compromise the association's security. This paper introduces PhishNot, a machine learning-based system for detecting phishing URLs. Here, AI can assume a significant part in adjusting the capacities of PC organizations to perceive phishing designs that are presently being used and are evolving. Therefore, our work depends intensely on "gaining from information" and is upheld by a delegate situation and dataset. The number of input features was reduced to 14 to guarantee the system's practical applicability. Experiments showed that Random Forest performed the best, with an accuracy of 97.5 per cent. Our system's design is even more adaptable when deployed in the cloud due to its high speed and high phishing detection rate (an average of 11.5 URLs per second).

References

• VrbančičG. et al.Datasets for phishing websites detection (2020), KhormaliA. et al.
• DTOF-ANN: An artificial neural network phishing detection model based on decision tree and optimal features Appl. Soft Comput. (2020), ChiewK.L. et al.
• A new hybrid ensemble feature selection framework for machine learning-based phishing detection system Inform. Sci. (2019), SahingozO.K. et al.
• Machine learning based phishing detection from URLs Expert Syst. Appl. (2019), RaoR.S. et al.
• Jail-Phish: An improved search engine based phishing detection system Comput. Secur. (2019), SonowalG. et al.
• PhiDMA–A phishing detection model with multi-filter approach J. King Saud Univ. Comput. Inf. Sci. (2020), KhonjiM. et al.
• Phishing detection: a literature survey IEEE Commun. Surv. Tutor. (2013), CaputoD.D. et al.
• Going spear phishing: Exploring embedded training and awareness IEEE Secur. Priv. (2013)
• Technical aspects of cyber kill chain ChinT. et al.
• Phishlimiter: A phishing detection and mitigation approach using software-defined networking IEEE Access (2018), WeiB. et al.
• A deep-learning-driven light-weight phishing detection sensor Sensors (2019), JainA.K. et al.
• A machine learning based approach for phishing detection using hyperlinks information J. Ambient Intell. Humaniz. Comput., (2019)

Back Download