Malicious URLs are a significant threat in cyberspace, facilitating phishing and data theft. Traditional filtering methods are inadequate against evolving cybercriminal tactics, highlighting the need for advanced predictive models. A study from the University of Hertfordshire introduces a hybrid model using machine learning and deep learning to enhance web security.
The proposed model combines Random Forest and Multilayer Perceptron algorithms, achieving an accuracy of 81% in identifying malicious URLs. This innovative approach not only improves detection rates but also offers computational efficiency, making it suitable for real-time applications. The research emphasizes the importance of integrating AI techniques to address complex cybersecurity challenges.
• Hybrid model combines machine learning and deep learning for URL prediction.
• Achieved 81% accuracy in identifying malicious URLs using advanced algorithms.
Machine learning techniques are utilized to predict malicious URLs effectively.
Deep learning enhances the model's ability to capture complex patterns in data.
Random Forest is used for its accuracy in handling complex datasets in the hybrid model.
Multilayer Perceptron excels in learning intricate data representations, complementing Random Forest.
The Financial Express 16month
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.