Divakarla, U.Chandrasekaran, K.2026-02-0620232023 3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023, 2023, Vol., , p. -https://doi.org/10.1109/SMARTGENCON60755.2023.10442775https://idr.nitk.ac.in/handle/123456789/29280Phishing attempts, which try to fool people into giving attackers valuable information like login credentials, credit card numbers, and personal data, have grown more frequent and sophisticated over time. According to the 2021 Verizon Data Breach Investigations Report, phishing attempts were the cause of 36% of data breaches in 2020, up from 25% in 2019, and 96% of these assaults were sent by email. A mix of user education, technical controls, and automated detection systems can be used to prevent phishing attempts, which are crucial for preserving cybersecurity. Since phishing efforts are continually changing and growing more complex, machine learning and deep learning techniques are very useful for detecting them. Extreme gradient boosting (XGBoost) and Random Forest algorithms were utilised in this work to construct automated models for spotting phishing emails and links. These algorithms had accuracy rates of 98.57% and 96.7%, respectively. These models enable organisations and people to proactively recognise and stop phishing assaults, lowering the risk of monetary losses and data breaches. © 2023 IEEE.Deep learning GAP analysisInformation security Machine Learning algorithmsPhishing Email detectionPhishing websites Natural language processing