Sylph: An Unsupervised APT Detection System Based on the Provenance Graph

Traditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaida Jiang, Zihan Gao, Siyu Zhang, Futai Zou
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406745146818560
author Kaida Jiang
Zihan Gao
Siyu Zhang
Futai Zou
author_facet Kaida Jiang
Zihan Gao
Siyu Zhang
Futai Zou
author_sort Kaida Jiang
collection DOAJ
description Traditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance graph, which not only detects APT attacks but also localizes APT attacks with a fine event granularity and feeds possible attacks back to system detectors to reduce their localization burden. Sylph proposes a whole-process architecture from provenance graph collection to anomaly detection, starting from the system audit logs, and dividing subgraphs based on time slices of the provenance graph it transforms into to reduce memory overhead. Starting from the system audit logs, the provenance graph it transforms into is divided into subgraphs based on time slices, which reduces the memory occupation and improves the detection efficiency at the same time; on the basis of generating the sequence of subgraphs, the full graph embedding of the subgraphs is carried out by using Graph2Vec to obtain their feature vectors, and the anomaly detection based on unsupervised learning is carried out by using an autoencoder, which is capable of detecting new types of attacks that have not yet appeared. After the experimental evaluation, Sylph can realize the APT attack detection with higher accuracy and achieve an accuracy rate.
format Article
id doaj-art-952b4b68601548ceb51936d9f8ea60cc
institution Kabale University
issn 2078-2489
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-952b4b68601548ceb51936d9f8ea60cc2025-08-20T03:36:18ZengMDPI AGInformation2078-24892025-07-0116756610.3390/info16070566Sylph: An Unsupervised APT Detection System Based on the Provenance GraphKaida Jiang0Zihan Gao1Siyu Zhang2Futai Zou3Network and Information Center, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, ChinaNetwork and Information Center, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, ChinaTraditional detection methods and security defenses are gradually insufficient to cope with evolving attack techniques and strategies, and have coarse detection granularity and high memory overhead. As a result, we propose Sylph, a lightweight unsupervised APT detection method based on a provenance graph, which not only detects APT attacks but also localizes APT attacks with a fine event granularity and feeds possible attacks back to system detectors to reduce their localization burden. Sylph proposes a whole-process architecture from provenance graph collection to anomaly detection, starting from the system audit logs, and dividing subgraphs based on time slices of the provenance graph it transforms into to reduce memory overhead. Starting from the system audit logs, the provenance graph it transforms into is divided into subgraphs based on time slices, which reduces the memory occupation and improves the detection efficiency at the same time; on the basis of generating the sequence of subgraphs, the full graph embedding of the subgraphs is carried out by using Graph2Vec to obtain their feature vectors, and the anomaly detection based on unsupervised learning is carried out by using an autoencoder, which is capable of detecting new types of attacks that have not yet appeared. After the experimental evaluation, Sylph can realize the APT attack detection with higher accuracy and achieve an accuracy rate.https://www.mdpi.com/2078-2489/16/7/566APT detectionprovenance graphgraph embedding
spellingShingle Kaida Jiang
Zihan Gao
Siyu Zhang
Futai Zou
Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
Information
APT detection
provenance graph
graph embedding
title Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
title_full Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
title_fullStr Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
title_full_unstemmed Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
title_short Sylph: An Unsupervised APT Detection System Based on the Provenance Graph
title_sort sylph an unsupervised apt detection system based on the provenance graph
topic APT detection
provenance graph
graph embedding
url https://www.mdpi.com/2078-2489/16/7/566
work_keys_str_mv AT kaidajiang sylphanunsupervisedaptdetectionsystembasedontheprovenancegraph
AT zihangao sylphanunsupervisedaptdetectionsystembasedontheprovenancegraph
AT siyuzhang sylphanunsupervisedaptdetectionsystembasedontheprovenancegraph
AT futaizou sylphanunsupervisedaptdetectionsystembasedontheprovenancegraph