Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Ruitong, Wang, Yanbin, Xu, Haitao, Qin, Zhan, Zhang, Fan, Liu, Yiwei, Cao, Zheng
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.12372
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910887245250560
author Liu, Ruitong
Wang, Yanbin
Xu, Haitao
Qin, Zhan
Zhang, Fan
Liu, Yiwei
Cao, Zheng
author_facet Liu, Ruitong
Wang, Yanbin
Xu, Haitao
Qin, Zhan
Zhang, Fan
Liu, Yiwei
Cao, Zheng
contents The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information, and local-global encoding integration. To address these challenges, we propose PMANet, a pre-trained Language Model-Guided multi-level feature attention network. PMANet employs a post-training process with three self-supervised objectives: masked language modeling, noisy language modeling, and domain discrimination, effectively capturing subword and character-level information. It also includes a hierarchical representation module and a dynamic layer-wise attention mechanism for extracting features from low to high levels. Additionally, spatial pyramid pooling integrates local and global features. Experiments on diverse scenarios, including small-scale data, class imbalance, and adversarial attacks, demonstrate PMANet's superiority over state-of-the-art models, achieving a 0.9941 AUC and correctly detecting all 20 malicious URLs in a case study. Code and data are available at https://github.com/Alixyvtte/Malicious-URL-Detection-PMANet.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12372
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network
Liu, Ruitong
Wang, Yanbin
Xu, Haitao
Qin, Zhan
Zhang, Fan
Liu, Yiwei
Cao, Zheng
Cryptography and Security
The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information, and local-global encoding integration. To address these challenges, we propose PMANet, a pre-trained Language Model-Guided multi-level feature attention network. PMANet employs a post-training process with three self-supervised objectives: masked language modeling, noisy language modeling, and domain discrimination, effectively capturing subword and character-level information. It also includes a hierarchical representation module and a dynamic layer-wise attention mechanism for extracting features from low to high levels. Additionally, spatial pyramid pooling integrates local and global features. Experiments on diverse scenarios, including small-scale data, class imbalance, and adversarial attacks, demonstrate PMANet's superiority over state-of-the-art models, achieving a 0.9941 AUC and correctly detecting all 20 malicious URLs in a case study. Code and data are available at https://github.com/Alixyvtte/Malicious-URL-Detection-PMANet.
title PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network
topic Cryptography and Security
url https://arxiv.org/abs/2311.12372