Detection of Phishing Mail, Cross-Site Scripting and SQL Injection Using Machine Learning
Machine learning techniques to detect threat identification.
The project aims to investigate machine learning techniques that can recognize Phishing Mail, Cross-Site Scripting, and SQL injection vulnerabilities in web applications. It proposes generating web application logs to process abnormal user actions and identify behaviours that breach the rules or are out of bounds. Additionally, the paper provides mitigations against common web application attacks and ways for web administrators to detect phishing emails, a prevalent social engineering attack.
Machine learning-based approaches offer a more robust and scalable solution to detect these types of attacks. By using algorithms that can learn from historical data and patterns, machine learning models can effectively identify and prevent phishing emails, cross-site scripting, and SQL injection attacks. These models can also be trained using large datasets and can adapt to new and evolving attack patterns, making them more effective than traditional approaches. However, it is important to note that machine learning-based approaches are not foolproof and can also have limitations. These models require a large amount of data to be trained effectively, and their accuracy can be affected by the quality of the training data. Additionally, attackers can also use adversarial techniques to bypass these models.