Downloads · 30 days
0
ICT3914-EMBER2024-Ensembles
Isaac-Zam/ICT3914-EMBER2024-Ensembles
ICT3914-EMBER2024-Ensembles is a text classification model from Isaac-Zam. Use it when you need a label for a piece of text.
Author: Isaac Zammit Supervisor: Prof. Christian Colombo Co-Supervisor: Dr Joseph Bugeja
Access
Public
Updated May 29, 2026
Repo size
235 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl119 GB · 99%
At a glance
- Task
- Text Classification
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 29, 2026
- SHA
- af519683
Try a prompt
Model card
From the Hugging Face model README
ICT3914 Tree-Based Ensemble Re-benchmarking of EMBER2024: Detecting Evasive and Emerging Threats
Author: Isaac Zammit
Supervisor: Prof. Christian Colombo
Co-Supervisor: Dr Joseph Bugeja
Overview
This repository contains all the trained models produced as part of the dissertation titled above. The tree-based ensemble architectures (LightGBM, XGBoost and Random Forest) were evaluated across the full EMBER2024 task suite in both untuned and tuned configurations.
Dataset
All models were trained on EMBER2024, available via the official thrember package: https://github.com/FutureComputing4AI/EMBER2024/
Model Naming Convention
| Prefix | Description |
|---|---|
LIGHTGBM_EMBER2024_* | Untuned LightGBM baseline |
TUNED_LIGHTGBM_EMBER2024_* | Tuned LightGBM |
XGB_EMBER2024_* | Untuned XGBoost baseline |
TUNED_XGB_EMBER2024_* | Tuned XGBoost |
RF_EMBER2024_* | Untuned Random Forest baseline |
TUNED_RF_EMBER2024_* | Tuned Random Forest |
Partition suffixes: all, AllPE, Win32, Win64,
Dot_Net, APK, ELF, PDF, family, behavior,
packer, exploit, file_property, group
- Task
- Text Classification
- Created
- May 19, 2026
- Updated
- May 29, 2026