Text Classification
Transformers
Safetensors
English
modernbert
cyber-threat-intelligence
mitre-attack
multi-label-classification
defensive-security
blue-team
threat-intelligence
text-embeddings-inference
Instructions to use ctokx/cti-attack-mapper-modernbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ctokx/cti-attack-mapper-modernbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ctokx/cti-attack-mapper-modernbert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ctokx/cti-attack-mapper-modernbert") model = AutoModelForSequenceClassification.from_pretrained("ctokx/cti-attack-mapper-modernbert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| cti-attack-mapper | |
| Copyright 2026 Varol Cagdas Tok | |
| Licensed under the Apache License, Version 2.0. | |
| Full text: https://www.apache.org/licenses/LICENSE-2.0 | |
| ------------------------------------------------------------------------------ | |
| THIRD-PARTY ATTRIBUTION | |
| ------------------------------------------------------------------------------ | |
| This work contains and derives from the following: | |
| 1. TRAM (Threat Report ATT&CK Mapper) | |
| MITRE Center for Threat-Informed Defense | |
| https://github.com/center-for-threat-informed-defense/tram | |
| Licensed under the Apache License, Version 2.0. | |
| The training corpus in data/build/ is derived from TRAM's | |
| data/tram2-data/multi_label.json by deduplication, boilerplate removal and | |
| re-splitting. No sentence text was rewritten. | |
| 2. MITRE ATT&CK STIX Data | |
| The MITRE Corporation | |
| https://github.com/mitre-attack/attack-stix-data | |
| Used under the ATT&CK Terms of Use: https://attack.mitre.org/resources/terms-of-use/ | |
| Used for technique names and the keyword baseline only. No ATT&CK content is | |
| redistributed in this repository; it is downloaded at build time. | |
| ATT&CK(R) is a registered trademark of The MITRE Corporation. This project is | |
| not affiliated with, endorsed by, or sponsored by The MITRE Corporation. | |
| ------------------------------------------------------------------------------ | |
| INTENDED USE | |
| ------------------------------------------------------------------------------ | |
| This model classifies descriptions of adversary behaviour that have already | |
| been published in public threat reporting. It is intended for defensive | |
| security work: threat intelligence triage, detection engineering, and | |
| coverage analysis. It does not generate offensive capability. | |