A Game-Based Adversarial DGA Detection Scheme Using Multi-Level Incremental Random Forest
- 24 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (1) , 779-792
Abstract
Security vendors can take down botnets by detecting the malicious domain names crafted by attackers. However, the adversarial Domain Generation Algorithms ( DGAs ) greatly challenge the existing domain detection schemes, in particular, adversarial DGAs can actively compromise arbitrarily specified domain detection systems by crafting the adversarial domain names. To resist adversarial DGAs, we propose a game theory-based defending strategy, which launches adversarial DGA and trains an incremental domain detector alternately. While we find the game-based strategy cannot achieve the expected detection accuracy due to two problems: the failure of incremental training and the problem of the catastrophic forgetting . To this end, we propose a multi-level incremental random forest model, which settles the above problems by splitting the leaf nodes of the decision trees and increasing the levels of the original random forest. The experimental results on the real-life dataset demonstrate the proposed detection method significantly outperforms the competing schemes when detecting adversarial DGAs (improves the detection AUC by 42%) and presents comparable performance when defending against non-adversarial DGAs.Keywords
Funding Information
- National Natural Science Foundation of China (61872265, 62141218, U1836214)
- New Generation of Artificial Intelligence Science and Technology (19ZXZNGX00010)
- Zhejiang Lab (2021DA0AM01/003)
This publication has 27 references indexed in Scilit:
- Botnet in DDoS Attacks: Trends and ChallengesIEEE Communications Surveys & Tutorials, 2015
- Nonparametric Statistics: A Step‐by‐Step ApproachInternational Statistical Review, 2015
- ExposureACM Transactions on Information and System Security, 2014
- Phoenix: DGA-Based Botnet Tracking and Intelligence2014
- Highly resilient peer-to-peer botnets are here: An analysis of Gameover Zeus2013
- Long Short-Term MemoryNeural Computation, 1997
- A survey of decision tree classifier methodologyIEEE Transactions on Systems, Man, and Cybernetics, 1991
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.Radiology, 1982
- Co‐citation in the scientific literature: A new measure of the relationship between two documentsJournal of the American Society for Information Science, 1973
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951