An end-to-end framework for private DGA detection as a service
PLOS ONE · 2024
DOI: 10.1371/journal.pone.0304476 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Ricardo J M Maia und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Brasilia, Federal District, Brasília, Brazil. Hauptthemen laut MEDLINE: Algorithms, Computer Security. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Domain Generation Algorithms (DGAs) are used by malware to generate pseudorandom domain names to establish communication between infected bots and command and control servers. While DGAs can be detected by machine learning (ML) models with great accuracy, offering DGA detection as a service raises privacy concerns when requiring network administrators to disclose their DNS traffic to the service provider. The main scientific contribution of this paper is to propose the first end-to-end framework for privacy-preserving classification as a service of domain names into DGA (malicious) or non-DGA (benign) domains. Our framework achieves these goals by carefully designed protocols that combine two privacy-enhancing technologies (PETs), namely secure multi-party computation (MPC) and differential privacy (DP). Through MPC, our framework enables an enterprise network administrator to outsource the problem of classifying a DNS (Domain Name System) domain as DGA or non-DGA to an external organization without revealing any information about the domain name. Moreover, the service provider’s ML model used for DGA detection is never revealed to the network administrator. Furthermore, by using DP, we also ensure that the classification result cannot be used to learn information about individual entries of the training data. Finally, we leverage post-training float16 quantization of deep learning models in MPC to achieve efficient, secure DGA detection. We demonstrate that by using quantization achieves a significant speed-up, resulting in a 23% to 42% reduction in inference runtime without reducing accuracy using a three party secure computation protocol tolerating one corruption. Previous solutions are not end-to-end private, do not provide differential privacy guarantees for the model’s outputs, and assume that model embeddings are publicly known. Our best protocol in terms of accuracy runs in about 0.22s.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, University of Brasilia, Federal District, Brasília, Brazil.
- School of Engineering, University of Washington Tacoma, Tacoma, Washington, United States of America.
- Department of Software Systems and Cybersecurity, Monash University, Melbourne, Australia.
- Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium.
- Visa Research (Work done while at University of Washington Tacoma), Foster City, California, United States of America.
ORCID-Profile: Ricardo J M Maia, Ricardo Jacobi
Zitieren
APA
Maia, R. J. M., Ray, D., Pentyala, S., Dowsley, R., De Cock, M., Nascimento, A. C. A., & Jacobi, R. (2024). An end-to-end framework for private DGA detection as a service. PLOS ONE. https://doi.org/10.1371/journal.pone.0304476
Vancouver
Maia RJM, Ray D, Pentyala S, Dowsley R, De Cock M, Nascimento ACA, et al. An end-to-end framework for private DGA detection as a service. PLOS ONE. 2024. doi:10.1371/journal.pone.0304476
BibTeX
@article{Maia2024,
author = {Maia, Ricardo J M and Ray, Dustin and Pentyala, Sikha and Dowsley, Rafael and De Cock, Martine and Nascimento, Anderson C A and Jacobi, Ricardo},
title = {An end-to-end framework for private DGA detection as a service},
journal = {PLOS ONE},
year = {2024},
doi = {10.1371/journal.pone.0304476}
}
EUVIMED