Robust DDoS-Attack Classification with 3D CNNs Against Adversarial Methods
This addresses the threat of DDoS attacks bypassing detection for online infrastructure, representing a strong specific gain in cybersecurity.
The paper tackled the problem of classifying Distributed Denial-of-Service (DDoS) attacks against adversarial methods, achieving an adversarial accuracy increase from 50-55% to over 93% while maintaining clean-sample performance.
Distributed Denial-of-Service (DDoS) attacks remain a serious threat to online infrastructure, often bypassing detection by altering traffic in subtle ways. We present a method using hive-plot sequences of network data and a 3D convolutional neural network (3D CNN) to classify DDoS traffic with high accuracy. Our system relies on three main ideas: (1) using spatio-temporal hive-plot encodings to set a pattern-recognition baseline, (2) applying adversarial training with FGSM and PGD alongside spatial noise and image shifts, and (3) analyzing frame-wise predictions to find early signals. On a benchmark dataset, our method lifts adversarial accuracy from 50-55% to over 93% while maintaining clean-sample performance. Frames 3-4 offer strong predictive signals, showing early-stage classification is possible.