Skip to content

Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection

Sep 2026 · 0 citations · 26 references
Computer Science

TL;DR

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.

View source

Similar papers

Open access 2026

TDNET: A Dual-Channel Injection Attack Detection Framework for Web Application Firewalls

This work proposes an injection attack detection framework, TDNET, that combines dual-channel feature extraction, multidimensional feature fusion, adaptive attention refinement, and time-sensitive neural architecture search optimization.

Congzhao Wen, Mingzhan Wu, Kongsheng Lin et al. · 0 citations
Preprint Aug 2026

X-WAD: eXplainable Web Anomaly Detection

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...

Matteo Bitussi, R. Doriguzzi-Corin · 0 citations
Review 2026

Hybrid Ensemble Learning For Malicious URL Detection: A Literature Review of Machine Learning, Deep Learning, and Feature-Fusion Approaches

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 · 0 citations
Open access Sep 2026

Hybrid Content- and Session-Based Anomaly Detection for Web Server Logs

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 · 0 citations
Conference Sep 2026

Intelligent Extraction of Static and Dynamic Invariants for Botnet Classification

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 · 0 citations
Open access Sep 2026

HTTP Anomaly Detection Using Character-Level 3-Gram TF-IDF and Hybrid TF-IDF–Hashing Representations: A Comparative Study of Machine Learning Models

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 · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.