IP-Augmented Multi-Modal Malicious URL Detection Via Token-Contrastive Representation Enhancement and Multi-Granularity Fusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tian, Ye, Yu, Yanqiu, Song, Liangliang, Liu, Zhiquan, Wang, Yanbin, Sun, Jianguo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912646084689920
author Tian, Ye
Yu, Yanqiu
Song, Liangliang
Liu, Zhiquan
Wang, Yanbin
Sun, Jianguo
author_facet Tian, Ye
Yu, Yanqiu
Song, Liangliang
Liu, Zhiquan
Wang, Yanbin
Sun, Jianguo
contents Malicious URL detection remains a critical cybersecurity challenge as adversaries increasingly employ sophisticated evasion techniques including obfuscation, character-level perturbations, and adversarial attacks. Although pre-trained language models (PLMs) like BERT have shown potential for URL analysis tasks, three limitations persist in current implementations: (1) inability to effectively model the non-natural hierarchical structure of URLs, (2) insufficient sensitivity to character-level obfuscation, and (3) lack of mechanisms to incorporate auxiliary network-level signals such as IP addresses-all essential for robust detection. To address these challenges, we propose CURL-IP, an advanced multi-modal detection framework incorporating three key innovations: (1) Token-Contrastive Representation Enhancer, which enhances subword token representations through token-aware contrastive learning to produce more discriminative and isotropic embeddings; (2) Cross-Layer Multi-Scale Aggregator, employing hierarchical aggregation of Transformer outputs via convolutional operations and gated MLPs to capture both local and global semantic patterns across layers; and (3) Blockwise Multi-Modal Coupler that decomposes URL-IP features into localized block units and computes cross-modal attention weights at the block level, enabling fine-grained inter-modal interaction. This architecture enables simultaneous preservation of fine-grained lexical cues, contextual semantics, and integration of network-level signals. Our evaluation on large-scale real-world datasets shows the framework significantly outperforms state-of-the-art baselines across binary and multi-class classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IP-Augmented Multi-Modal Malicious URL Detection Via Token-Contrastive Representation Enhancement and Multi-Granularity Fusion
Tian, Ye
Yu, Yanqiu
Song, Liangliang
Liu, Zhiquan
Wang, Yanbin
Sun, Jianguo
Cryptography and Security
Malicious URL detection remains a critical cybersecurity challenge as adversaries increasingly employ sophisticated evasion techniques including obfuscation, character-level perturbations, and adversarial attacks. Although pre-trained language models (PLMs) like BERT have shown potential for URL analysis tasks, three limitations persist in current implementations: (1) inability to effectively model the non-natural hierarchical structure of URLs, (2) insufficient sensitivity to character-level obfuscation, and (3) lack of mechanisms to incorporate auxiliary network-level signals such as IP addresses-all essential for robust detection. To address these challenges, we propose CURL-IP, an advanced multi-modal detection framework incorporating three key innovations: (1) Token-Contrastive Representation Enhancer, which enhances subword token representations through token-aware contrastive learning to produce more discriminative and isotropic embeddings; (2) Cross-Layer Multi-Scale Aggregator, employing hierarchical aggregation of Transformer outputs via convolutional operations and gated MLPs to capture both local and global semantic patterns across layers; and (3) Blockwise Multi-Modal Coupler that decomposes URL-IP features into localized block units and computes cross-modal attention weights at the block level, enabling fine-grained inter-modal interaction. This architecture enables simultaneous preservation of fine-grained lexical cues, contextual semantics, and integration of network-level signals. Our evaluation on large-scale real-world datasets shows the framework significantly outperforms state-of-the-art baselines across binary and multi-class classification tasks.
title IP-Augmented Multi-Modal Malicious URL Detection Via Token-Contrastive Representation Enhancement and Multi-Granularity Fusion
topic Cryptography and Security
url https://arxiv.org/abs/2510.12395