Distributed Denial of Services: Detection and Prevention

Abstract

Listen

Translate article

Distributed Denial of Service is one of the most prominent and dangerous types of attacks dis- rupting critical online services, suffering finan- cial losses, and affecting organizational oper- ations. The exploitation of vulnerabilities is enough to overwhelm the targeted websites with malicious traffic, making them inaccessible to legitimate users. Such sophistication in attack patterns coupled with explosive growth in con- nected devices has challenged the traditional approaches of detection, being bare minimum signature-based or basic anomaly detection and likely to pose difficulties in coping with emerging threats, thus prone to high false positives. This paper presents a systematic review of ten works from very recent literature on ML and DL applications in DDoS detection and mit- igation. The techniques thus are supervised, unsupervised, and hybrids applied to datasets such as NSL-KDD, CICIDS2017. ML and DL techniques do appear promising for increas- ing accuracy in detection and adaptability, but then challenges persist-in scalability, efficiency or speed of computation, and quality of datasets. It would challenge the future of research: more light on real- time models, more diversified and all-inclusive datasets, and edge and federated computing towards better accelerated detection. These would significantly contribute to the ad- vancement of scalable effective solutions that counter complex DDoS threats in today’s net- work environments. Keywords Distributed Denial of Service (DDoS) Attacks, Cybersecurity, Network Traffic Anomaly De- tection, Real-Time Threat Detection, Machine Learning (ML), Deep Learning (DL), Hy- brid Detection Models, Anomaly Detection, Signature- Based Detection, Adaptive Security Models.