Cybersecurity-Knowledge-Graph Open-Source Model - Freely Extract Information from Cybersecurity Texts to Build Knowledge Graphs

Cybersecurity Knowledge Graph

Developed by CyberPeace-Institute

Fine-tuned based on the SecureBERT framework for extracting event cores, arguments, and their relationships from cybersecurity texts to construct knowledge graphs.

Knowledge Graph

Transformers

EnglishOpen Source License:MIT #Event Argument Extraction #Security Event Graph Construction #Multi-role Relationship Analysis

Downloads 548

Release Time : 9/19/2023

Model Overview

This model can identify event cores, arguments, and their semantic relationships from cybersecurity-related texts, supporting the determination of event reality (actual/not occurred/generic events), fully implementing the technical solution of the CASIE paper.

Model Features

Multi-level Event Analysis

Simultaneously identifies event cores (multi-word phrases), participating arguments, and their semantic role relationships.

Reality Determination

Can distinguish whether events actually occurred (Actual), did not occur (Other), or are conceptually mentioned (Generic).

Domain-specific Adaptation

Fine-tuned based on the cybersecurity-specific SecureBERT framework, optimized for cybersecurity texts.

Model Capabilities

Cybersecurity Event Identification

Semantic Role Labeling

Knowledge Graph Construction

Event Reality Determination

Use Cases

Security Intelligence Analysis

Attack Event Structuring

Automatically extracts attack event elements (attacker, target, method, time, etc.) from security reports.

Generates standardized event knowledge graphs.

Threat Intelligence Processing

Automated Intelligence Extraction

Processes large volumes of threat intelligence data to automatically identify key security events and their related entities.

Improves intelligence processing efficiency.

🚀 Knowledge Graph Extraction for Cyber incidents

This model is fine - tuned with SecureBERT on the CASIE dataset, aiming to extract knowledge graphs for cyber - incidents.

🚀 Quick Start

This model has been finetuned with SecureBERT (https://arxiv.org/abs/2204.02685) on the CASIE dataset (https://ieeexplore.ieee.org/document/9776031). We have implemented the approach described in the CASIE paper.

📚 Documentation

The following description is taken from the CASIE paper:

An event nugget is a word or phrase that most clearly expresses the event occurrence. These differ from event triggers in that they can be multi - word phrases.
An event argument is an event participant or property value. They can be taggable entities involved in the event, such as person or organization, or attributes that specify important information, such as time or amount.
A role is a semantic relation between an event nugget and an argument. Each event type specifies the roles it can have and constraints on the arguments that can fill them.
A realis value specifies whether or not an event occurred and can be one of the three values: Actual (event actually happened), Other (failed event, future event), or Generic (an undetermined/non - specific event, such as referring to the concept of phishing attacks).

💻 Usage Examples

Basic Usage

from transformers import AutoModelForTokenClassification
model = AutoModelForTokenClassification.from_pretrained("CyberPeace-Institute/Cybersecurity-Knowledge-Graph", trust_remote_code=True)

input_text = "This is a Cybersecurity-related text."

output = model(input_text)

Advanced Usage

# IMPORTANT! : To get the Argument to Role coreferences, use the dedicated **space**! You can download the models under "arg_role_models/".
from transformers import AutoModelForTokenClassification
model = AutoModelForTokenClassification.from_pretrained("CyberPeace-Institute/Cybersecurity-Knowledge-Graph", trust_remote_code=True)

input_text = "This is a Cybersecurity-related text."

output = model(input_text)

📄 License

This project is licensed under the MIT license.

Property	Details
Pipeline Tag	token - classification
Tags	legal
License	mit

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご