DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Chaeyoung, Jung, Chaeri, Jeong, Seonghoon
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913112536383488
author Lee, Chaeyoung
Jung, Chaeri
Jeong, Seonghoon
author_facet Lee, Chaeyoung
Jung, Chaeri
Jeong, Seonghoon
contents Domain Generation Algorithms (DGAs) evolve continuously to evade botnet detection, posing a persistent challenge for dependable network defense. While deep learning-based detectors achieve strong performance under static conditions, they suffer severe degradation when facing temporal drift. Through a 9-year longitudinal study (2017-2025), we empirically show that state-of-the-art character- and word-based DGA classifiers rapidly lose effectiveness as new DGA variants emerge. To address this problem, we propose a drift-resilient Transformer-based framework that learns invariant representations through a hybrid tokenization strategy and multi-task self-supervised pre-training. The model integrates (i) character-level encoding to capture stochastic morphological patterns and (ii) subword-level encoding for word-based DGAs. Three pre-training tasks enable the model to learn robust structural and contextual features prior to supervised fine-tuning. Comprehensive evaluations demonstrate that our method significantly mitigates temporal degradation and consistently outperforms state-of-the-art baselines in forward-chaining experiments. The proposed approach offers a dependable foundation for long-term DGA defense in evolving threat landscapes. Our code is available at: https://github.com/snsec-net/2026-DSN-DRIFT.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10436
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
Lee, Chaeyoung
Jung, Chaeri
Jeong, Seonghoon
Cryptography and Security
Machine Learning
Networking and Internet Architecture
68T07, 68M25
C.2.0; I.2.6; K.6.5
Domain Generation Algorithms (DGAs) evolve continuously to evade botnet detection, posing a persistent challenge for dependable network defense. While deep learning-based detectors achieve strong performance under static conditions, they suffer severe degradation when facing temporal drift. Through a 9-year longitudinal study (2017-2025), we empirically show that state-of-the-art character- and word-based DGA classifiers rapidly lose effectiveness as new DGA variants emerge. To address this problem, we propose a drift-resilient Transformer-based framework that learns invariant representations through a hybrid tokenization strategy and multi-task self-supervised pre-training. The model integrates (i) character-level encoding to capture stochastic morphological patterns and (ii) subword-level encoding for word-based DGAs. Three pre-training tasks enable the model to learn robust structural and contextual features prior to supervised fine-tuning. Comprehensive evaluations demonstrate that our method significantly mitigates temporal degradation and consistently outperforms state-of-the-art baselines in forward-chaining experiments. The proposed approach offers a dependable foundation for long-term DGA defense in evolving threat landscapes. Our code is available at: https://github.com/snsec-net/2026-DSN-DRIFT.
title DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
topic Cryptography and Security
Machine Learning
Networking and Internet Architecture
68T07, 68M25
C.2.0; I.2.6; K.6.5
url https://arxiv.org/abs/2605.10436