Acti
The Acti dataset, created by Beihang University, focuses on mining cybersecurity threat intelligence entities and their relations for autonomous driving vehicles. It contains 908 real automotive cybersecurity reports, comprising 3,678 sentences, 8,195 security entities, and 4,852 semantic relations. Data were collected from the National Vulnerability Database and specific automotive threat intelligence platforms, and annotated using a BIOES joint labeling scheme. The dataset is primarily used for modeling automotive cybersecurity threat intelligence, aiming to extract valuable information from large volumes of cybersecurity data for proactive defense.
Dataset description and usage context
Automotive-cyber-threat-intelligence-corpus
Dataset Overview
This dataset is used for modeling cyber threat intelligence for autonomous driving vehicles.
Experimental Environment
- NVIDIA GeForce RTX 3090 GPU
- Python 3.7
- CUDA 11.2
- PaddlePaddle‑GPU 2.3.2
- paddlenlp 2.1.1
Data Description
- Raw Data: Unstructured cybersecurity data (.txt files)
- Brat Annotated Data: Annotation files produced with the brat tool (.ann files)
- BIOES: "BIOES" - "Entity Type" - "Relation Type" - "Entity Role" joint annotation data (.txt files)
Source Code Description
- Format Conversion: BIOES联合标注.py
- Pre‑processing: read.py; preprocess.py
- Deep Learning Model Training: BERT‑BiLSTM‑att‑CRF; BiLSTM‑dynamic‑att‑LSTM
Brat Tool
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.