Malicious website identification using design attribute learning

Naim, Or; Cohen, Doron; Ben‐Gal, Irad

doi:10.1007/s10207-023-00686-y

Cited by 6 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Naim O. et al [50] address the identification of malicious websites at page-level design. Therefore, starting from a URL, it is classified as malicious or legitimate according to the features of the website to which it points.…”

Section: Handle Class Imbalance In Web Phishing Classificationmentioning

confidence: 99%

Unbalanced Web Phishing Classification through Deep Reinforcement Learning

Maci,

Santorsola,

Coscia

et al. 2023

Computers

View full text Add to dashboard Cite

Web phishing is a form of cybercrime aimed at tricking people into visiting malicious URLs to exfiltrate sensitive data. Since the structure of a malicious URL evolves over time, phishing detection mechanisms that can adapt to such variations are paramount. Furthermore, web phishing detection is an unbalanced classification task, as legitimate URLs outnumber malicious ones in real-life cases. Deep learning (DL) has emerged as a promising technique to minimize concept drift to enhance web phishing detection. Deep reinforcement learning (DRL) combines DL with reinforcement learning (RL); that is, a sequential decision-making paradigm in which the problem to be addressed is expressed as a Markov decision process (MDP). Recent studies have proposed an ad hoc MDP formulation to tackle unbalanced classification tasks called the imbalanced classification Markov decision process (ICMDP). In this paper, we exploit the ICMDP to present a double deep Q-Network (DDQN)-based classifier to address the unbalanced web phishing classification problem. The proposed algorithm is evaluated on a Mendeley web phishing dataset, from which three different data imbalance scenarios are generated. Despite a significant training time, it results in better geometric mean, index of balanced accuracy, F1 score, and area under the ROC curve than other DL-based classifiers combined with data-level sampling techniques in all test cases.

show abstract

Section: Handle Class Imbalance In Web Phishing Classificationmentioning

confidence: 99%

Unbalanced Web Phishing Classification through Deep Reinforcement Learning

Maci,

Santorsola,

Coscia

et al. 2023

Computers

View full text Add to dashboard Cite

show abstract

“…This assessment involves utilizing various mathematical and statistical tools to quantify the likelihood of different risks and to assess the potential impact of such risks if they occur. The aim of situational quantitative assessment is to provide decision-makers with the necessary information to develop effective mitigation strategies, contingency plans, and response actions [13].…”

Section: Situational Quantitative Assessmentmentioning

confidence: 99%

Using Information Technology to Quantitatively Evaluate and Prevent Cybersecurity Threats in a Hierarchical Manner

Mai¹

2023

Int. J. Appl. Inf. Manag.

View full text Add to dashboard Cite

The vulnerability of traditional network security technology in the face of rapid advancements in information technology and the constant changes in network security. As a result, hackers can easily exploit loopholes in traditional security measures, such as cracking cryptographic algorithms, and stealing sensitive user information and data, which has led to a crisis of trust in recent years. To ensure safe and effective operation of massive data on the network, this article presents a quantitative assessment of the network's threat situation. The assessment is divided into two parts: support evaluation and credibility evaluation. These parts are further broken down into three levels of evaluation and severity evaluation. The article also provides a list of network security-related precautions that can be taken to mitigate potential risks. The experimental results show that implementing these hierarchical security measures can improve the security rate of Internet users' information by 4%-5%. Overall, the article highlights the importance of adopting more advanced and sophisticated security measures to combat the increasingly complex threats posed by cybercriminals.

show abstract

“…In the past few years, the field of external chain detection has witnessed a shift toward deep learning-based approaches driven by the rapid advancements in machine learning and artificial intelligence technology. According to the existing literature, text features are mostly used, and due to the variable length of Chinese text on web pages (Naim et al, 2023), in order to achieve the feasibility of model training, in addition to short text features such as Uniform Resource Locator(URL) and tags, part of text content from web pages is generally extracted for model training, resulting in poor practicability of the trained model. In addition, with the development of communication technology, a large number of web pages contain not only text information but also a lot of multimedia information, such as pictures, videos, and sounds.…”

mentioning

confidence: 99%

An Abnormal External Link Detection Algorithm Based on Multi-Modal Fusion

2024

International Journal of Information Security and Privacy

View full text Add to dashboard Cite

Website link detection is an important means to ensure the security of the external chain. In the past, it was mainly realized through blacklisting and feature engineering-based machine learning, which has the problems of slow detection speed and weak model generalization ability. The development of neural networks has brought a new solution to the security detection of the external chain of the website. To address the performance bottleneck caused by the variable content length of web pages, this article introduces an innovative approach: a website external link security detection algorithm based on multi-modal fusion. It extracts text, dynamic script, and image features separately, and constructs a deep fusion model that combines these multi-modal features. Compared with the previous research results, the proposed method is superior to the traditional single-mode method, and can quickly and accurately identify malicious web pages. The accuracy and F1 value are improved by 2.7% and 0.026.

show abstract

Malicious website identification using design attribute learning

Cited by 6 publications

References 56 publications

Unbalanced Web Phishing Classification through Deep Reinforcement Learning

Unbalanced Web Phishing Classification through Deep Reinforcement Learning

Using Information Technology to Quantitatively Evaluate and Prevent Cybersecurity Threats in a Hierarchical Manner

An Abnormal External Link Detection Algorithm Based on Multi-Modal Fusion

Contact Info

Product

Resources

About