HEDA (HTTP Embedding-Based Detection Architecture), a modular detection pipeline that combines static embedding representations with single-class anomaly detection models to detect anomalies at the request level, is proposed.
Abstract
Web applications are increasingly targeted by cyberattacks that exploit HTTP requests to evade security mechanisms. Traditional web application firewalls (WAFs) rely on rule-based approaches that often exhibit high false positive rates and limited adaptability. Recent studies have explored machine learning techniques and word embedding models to improve anomaly detection in HTTP traffic. This paper presents a benchmark for static embedding models, specifically Word2Vec, FastText, and Doc2Vec, within a unified, single-class classification framework. We propose HEDA (HTTP Embedding-Based Detection Architecture), a modular detection pipeline that combines static embedding representations with single-class anomaly detection models to detect anomalies at the request level. The approach operates in an unsupervised environment, where both the embedding models and detectors are trained exclusively on benign HTTP traffic. The proposed methodology is evaluated on three datasets with heterogeneous characteristics, including both synthetic and real traffic. The experimental results show that the choice of embedding representation significantly affects detection performance, and that FastText-based embeds produce the most consistent results across all datasets, achieving high detection rates while keeping false positive rates under control.
This paper investigates the effectiveness of Transformer-based Language Models in the detection of anomalies in HTTP requests, focussing on providing detailed explanations for the detected anomalies, and employs token-level logit-based surprisal mapping to provide both an anomaly score and a direct, detailed explanatio...
The rapid evolution of phishing, malware distribution, and other web-based attacks has made malicious Uniform Resource Locator (URL) detection an important cybersecurity research problem. Traditional blacklist and rule-based mechanisms provide efficient protection against known malicious addresses but may fail when att...
Ashwini B. Sable, Vijay More· International Journal of Lat...· 0 citations
Rule-based inspection of web server logs cannot detect attacks it has not already been told to look for, and most anomaly-detection studies validate their methods on a single dataset, which risks overstating how well a method generalises to new traffic. This paper presents a hybrid framework that fuses a content-based...
Abdul Rehman, Mouhammad Nouman, Muhsin Hassanu· Future Internet· 0 citations
The rapid mutation and obfuscation techniques employed by modern polymorphic botnets create a highly dynamic and non-stationary distribution of malware signatures, rendering traditional detection algorithms obsolete. This paper addresses the challenge of identifying such evasive threats by proposing a machine learning-...
Andrii Holovatiuk, Oleg Savenko· Automation, Control, and Inf...· 0 citations
Web applications are frequent targets of cyberattacks such as SQL injection, cross-site scripting, and command injection, creating a need for accurate and computationally efficient anomaly detection systems. While recent approaches increasingly rely on deep learning and transformer-based architectures, these methods of...
Mohinpasha Shaik, Siva Ganesh Varma Paidi, Mohammad Hassanzadeh· Computer and Information Sci...· 0 citations