MULTI-OBJECTIVE FIREFLY OPTIMIZATION ALGORITHM  FOR PHISHING ATTACK DETECTION USING ARTIFICIAL NEURAL NETWORK MODEL

Computer Engineering

Phishing attacks exert a significant influence on the internet, yielding financial setbacks, identity misappropriation and data infringements. They undermine trust in online dealings and impair email sender credibility. These assaults frequently propagate malware and filch login particulars, resulting in compromised websites and services. Phishing incidents diminish productivity in enterprises and have the potential to disseminate disinformation. The defence against phishing depletes substantial resources and exerts a global economic impact. In a nutshell, phishing attacks wield extensive ramifications on individuals, entities, and the broader internet ecosystem. There are various evolutionary algorithms introduced to provide the solutions. Multi Objective firefly optimization algorithm combines multiple objectives to enhance performance of a detection model. It draws inspiration from the collective behaviour of fireflies. The algorithm aims to strike a balance between reducing both false positives and false negatives, all the while striving to attain a diverse set of objectives, such as Accuracy, Recall, precision and F1-score. This will ultimately enhance the overall effectiveness of the detection process. The proposed algorithm offers a robust countermeasure against evolving and adaptable phishing strategies, displaying remarkable resistance to attacks of varying degrees of complexity.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.