AN EXPLAINABLE MULTI-MODAL HIERARCHICAL ATTENTION MODEL FOR DEVELOPING PHISHING THREAT INTELLIGENCE
DOI:
https://doie.org/10.5281/0q6gbh92Keywords:
Data Mining, Phishing, URL, RF,,Abstract
Today, phishing is one of the most dangerous online risks since it allows malicious websites to
steal users' login information. Sites that use phishing to steal users' personal information. sensitive information
when they browse a phony website. Website that seems like the real thing is another Internet crime is on the
rise, and it's one of the most in particular worries about several other sectors, including electronic account
management and retail. Phishing is, in general, a large-scale fraud that occurs when a rogue website behave
like a genuine server. The identification of phishing websites is a real and a complex and ambiguous matter
with many factors and unreliable standards of evaluation. This article describes a method which can identify
and stop both preexisting and freshly created threats URLs used in phishing attacks that have absolutely no
history of any kind evaluate the use of Data Mining. An online sorting system model will be developed for
the same, with many taken from parameters obtained from the URL's properties. The model will be taught to
recognize patterns in a large dataset to maximize precision and precision. Random Forest was used for this
purpose. (RF) is a subset of machine-learning-based Phishing website detection algorithms. Now, at long last,
we Delete the website from our network.
References
Listed as Reference: Ahmed, Abdulghani Ali, and Nurul Amirah Abdullah.
There is now "real-time detection of phishing websites." IEEE's 7th Annual Conference on Information
Technology, Electronics, and Mobile Communication (IEMCON), 2016.
Hawanna, Varsharani Ramdas; Kulkarni, V. Y.; and Rane, R. A. "A new algorithm for spotting malicious
URLs," it reads.
IEEE, 2016, pp. 548-552, International Conference on Automatic Control and Dynamic Optimization
Techniques (ICACDOT).
Jain, Ankit Kumar, and B. B. Gupta. Phishing detection method comparison using machine learning and
feature comparison. 2016 Third International Conference on Computing for Sustainable Global Development
(INDIACom). IEEE. pp. 2125-2130.
According to
Tahir, M. Amaad Ul Haq, et al. 2016 IEEE International Conference on Computational Science and
Computational Intelligence (CSCI), "A Hybrid Model to Detect Phishing Sites Using Supervised Learning
Algorithms." pp. 1126-1133.
Singh, Priyanka; Maravi, Yogendra P.; Sharma, Sanjeev. IEEE, 2015. "Phishing websites detection using
supervised learning networks." Proceedings of the 2015 International Conference on Computing and
Communications Technologies (ICCCT), pp. 61-65.
Phishing Statistics That You Need to Know, by J. Crowe
. [Online]. Available: https://blog.barkly.com/phishingstatistics-2016.
