SecEmbed
Collection
Cybersecurity embeddings: SecEmbed bi-encoders, SecReranker, training pairs, and retrieval benchmark. • 9 items • Updated
SecEmbed-small
Cybersecurity dense embedding model continued from BAAI/bge-small-en-v1.5 on secembed-pairs using MultipleNegativesRankingLoss with hard negatives.
Usage
python from sentence_transformers import SentenceTransformer model = SentenceTransformer("alirezaaminzadeh/SecEmbed-small") emb = model.encode(["detect powershell encoded command", "T1059.001 PowerShell..."])
Cascade
Use with SecReranker: retrieve top-50 with SecEmbed, rerank to top-5.
Training
- Loss: MultipleNegativesRankingLoss
- Data: ATT&CK, Sigma, CVE, CWE, SOC playbook triplets
- Hardware: Hugging Face ZeroGPU
- Downloads last month
- -
Model tree for alirezaaminzadeh/SecEmbed-small
Base model
BAAI/bge-small-en-v1.5