ATTACK BERT

🚀 ATT&CK BERT: a Cybersecurity Language Model

ATT&CK BERT is a domain - specific language model tailored for cybersecurity. It is built upon sentence - transformers. This model maps sentences depicting attack actions to semantically meaningful embedding vectors. For sentences with similar meanings, their embedding vectors exhibit high cosine similarity, which is useful for various cybersecurity applications.

🚀 Quick Start

✨ Features

• Domain - Specific: Focused on the cybersecurity domain, making it highly relevant for attack - related text analysis.
• Semantic Mapping: Maps sentences to embedding vectors, enabling semantic similarity calculations.

📦 Installation

Using this model becomes easy when you have sentence - transformers installed. Run the following command:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer
sentences = ["Attacker takes a screenshot", "Attacker captures the screen"]

model = SentenceTransformer('basel/ATTACK-BERT')
embeddings = model.encode(sentences)

from sklearn.metrics.pairwise import cosine_similarity
print(cosine_similarity([embeddings[0]], [embeddings[1]]))

📚 Documentation

To use ATT&CK BERT to map text to ATT&CK techniques, check our tool SMET: https://github.com/basel - a/SMET

📄 License

This project is licensed under the apache - 2.0 license.