Multi-Modal Clustering Discovery Method for Illegal Websites Based on Network Surveying and Mapping Big Data

Article Computer Science, Information Systems

A Deep Learning-Based Framework for Phishing Website Detection

Lizhen Tang et al.

Summary: This paper proposes a deep learning-based framework for detecting phishing websites and implements it as a browser plug-in for real-time prediction. Experimental results demonstrate the high accuracy of the framework.

IEEE ACCESS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Multi-scale semantic deep fusion models for phishing website detection

Dong-Jie Liu et al.

Summary: This paper proposes three semantic-based phishing detection models and demonstrates their good performance on a complex dataset and in a real network environment through experiments.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Computer Science, Information Systems

A Hybrid Multimodal Data Fusion-Based Method for Identifying Gambling Websites

Chenyang Wang et al.

Summary: With the development of network technology, the number of gambling websites has increased significantly, posing a threat to social stability. Existing methods for identifying gambling websites analyze the URL, text, and images of the websites, with most methods overlooking the text within the website images. However, these texts provide key information for accurately identifying gambling websites. Therefore, the challenge lies in effectively fusing image and text data.

ELECTRONICS (2022)

Add to Collection

Article Computer Science, Information Systems

Multilayer Stacked Ensemble Learning Model to Detect Phishing Websites

Lakshmana Rao Kalabarige et al.

Summary: This paper proposes a multilayered stacked ensemble learning technique to counter phishing attacks, achieving significant performance in various datasets.

IEEE ACCESS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Porn2Vec: A robust framework for detecting pornographic websites based on contrastive learning

Jun Zhao et al.

Summary: A new method named Porn2Vec is proposed in this paper for detecting pornographic websites using contrastive learning, which models heterogeneous graphs and learns high-level representations to effectively detect well-disguised pornographic websites. This method outperforms existing state-of-the-art methods and shows more promising and robust performance.

KNOWLEDGE-BASED SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence