Hierarchical Adversarially-Driven Escalation System(HADES)for Network Intrusion DetectionOA
Machine learning has radically transformed network security,enabling intrusion detection systems capable of identifying malicious traffic with near-perfect accuracy on standard benchmarks.However,these systems remain critically vulnerable to adversarial examples—subtly manipulated inputs designed to escape detection—where performance can severely drop under minimal perturbation.This paper introduces the Hierarchical Adversarially-Driven Escalation System(hades),a framework that addresses this vulnerability through three coordinated mechanisms.First,dedicated detectors are trained for each network protocol,enabling each model to specialize in specific traffic patterns it will face in practice.Second,these detectors are continuously hardened by simulating an arms race between an attacking agent,which learns to find the most damaging evasion strategies,and a defending model that adapts in response,thus producing classifiers that remain robust across a wide range of attack types.Third,incoming traffic is routed through a cost-aware pipeline that reserves expensive analysis for uncertain or suspicious flows,keeping average processing time at 5.4 ms per batch on normal traffic.hades is evaluated on CIC-IDS-2018,a large-scale real-world network dataset,and maintains near-perfect detection accuracy under both normal and adversarial conditions,with robustness verified across nine distinct attack strategies and 95%bootstrap confidence intervals of maximum width 0.0007.
Abdelouahid Derhab;Adlen Kerboua;Noureddine Seddari;Anis Haniche;Mohammad Mehedi Hassan
Center of Excellence in Information Assurance(CoEIA),King Saud University,Riyadh,Saudi ArabiaLGMM Laboratory,University 20 Août 1955-Skikda,Skikda,AlgeriaLICUS Laboratory,Department of Computer Science,University 20 Août 1955-Skikda,Skikda,Algeria Future Technology Laboratory,University of Parma,Parco Area delle Scienze 181/A,Parma,ItalySecDevOPS Consulting,61 Rue de Lyon,Paris,FranceDepartment of Information Systems,College of Computer and Information Sciences,King Saud University,Riyadh,Saudi Arabia
信息技术与安全科学
Network intrusion detectionadversarial robustnessadversarial trainingprotocol-stratified detectionmulti-tier cascadeparameter-efficient learning
《Computer Modeling in Engineering & Sciences》 2026 (9)
P.1607-1647,41
评论