Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178610,
        author = {Shreya Patil and Snehal Patil and Amruta Patil and Prof. Monica Charate},
        title = {Detection and Mitigation of DDoS Attacks with Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4323-4330},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178610},
        abstract = {With the quick development of the Web of Things (IoT), cybersecurity dangers have progressively ended up a major concern, particularly Disseminated Dissent of Benefit (DDoS) assaults. These assaults meddled with organize operations by overpowering them with intemperate activity, driving to disturbances. systems by assaulting them with over the top pernicious activity, which can result in downtime, money related misfortunes, and operational challenges. Later ponders highlight an disturbing increment in modern DDoS assaults particularly focusing on IoT gadgets. Due to their constrained security components, these gadgets are as often as possible abused to make large-scale botnets, such as Mirai, which have been responsible for a few of the foremost troublesome cyberattacks in later a long time. Conventional security measures, counting rule-based interruption location frameworks and manual activity sifting, frequently drop brief in giving real-time reactions, clearing out systems helpless to delayed benefit interferences. To address these challenges, this paper proposes a machine learning-driven DDoS location and computerized moderation framework planned to improve organize security in IoT environments. The framework leverages a crossover irregular timberland demonstrate to examine and classify organize activity, recognizing between authentic and noxious movement with tall precision. Past fundamental assault discovery, the framework classifies DDoS assaults into particular categories—including UDP surge, TCP SYN surge, HTTP surge, and ICMP flood—each of which misuses interesting organize vulnerabilities. UDP surges overpower targets with over the top parcels, TCP SYN surges misuse the TCP handshake prepare, HTTP surges imitate genuine web demands to debilitate server assets, and ICMP surges produce tall volumes of ping demands to stuff systems.},
        keywords = {DDoS Detection, Machine Learning, Random Forest, Firewall, Network Security, HTTP flood, ICMP flood, TCP SYN flood, UDP flood.},
        month = {May},
        }