Machine Learning-Based Approach to Mitigate DDoS Attacks Developed

Researchers at Xidian University in Guangzhou, China, have developed a novel DDoS defense mechanism, CRH4DDoS, which employs conflict resolution strategies for the integration of heterogeneous data. This approach addresses the challenges associated with existing machine learning-based approaches, including the need for pre-existing databases of DDoS incidents and performance limitations due to statistical analysis. CRH4DDoS conceptualizes network traffic as heterogeneous data and frames the identification of malicious traffic as a conflict resolution problem.

Key Takeaways:

• The Economical Intelligent DDoS Demotivation (EID) algorithm, introduced in a study published at CCS'21, demonstrates effective defense against DDoS attacks but is marred by a high false positive rate.
• The proposed CRH4DDoS approach does not necessitate a pre-existing DDoS database, achieves superior performance metrics, and markedly diminishes the false positive rate.
• Empirical assessments conducted on the real-world network platform reveal that the proposed CRH4DDoS is capable of defending against a variety of hybrid and dynamic DDoS attacks, occurring within seconds, with a false positive rate of merely 0.73%.
• The research has been peer-reviewed and assumes significant potential in the field of cybersecurity, particularly in the context of Internet of Things (IoT) services.
• The CRH4DDoS approach is novel in its ability to integrate heterogeneous data and utilize conflict resolution strategies for DDoS defense, addressing existing limitations in machine learning-based approaches.
• This research highlights the importance of innovative approaches to tackling the growing threat of DDoS attacks in IoT services.

Statistics:

• The proposed CRH4DDoS approach has a false positive rate of 0.73%.
• Empirical assessments were conducted on a real-world network platform to evaluate the performance of the CRH4DDoS approach.
• The CRH4DDoS approach is capable of defending against a variety of hybrid and dynamic DDoS attacks within seconds.

Sources:

• Defending Against Ddos Attacks Via Heterogeneous Data Conflict Resolution for Secure Services In Internet of Things. Ieee Transactions On Emerging Topics In Computational Intelligence, 2025.
• Ieee Transactions On Emerging Topics In Computational Intelligence can be contacted at: Ieee-inst Electrical Electronics Engineers Inc, 445 Hoes Lane, Piscataway, NJ 08855-4141, USA.
• Authors:

+ Bowen Zhao, Xidian University

+ Yang Xiao, Qingqi Pei, Jiakui Xiang, Cheng Qiao, Muhammad Shafiq and Mohammad Mahtab Alam.