ACSE-Eval/ACSE-Eval

ACSE-Eval数据集包含用于确定LLM威胁建模能力的AWS部署场景和它们的威胁模型。数据集包括100多个不同的AWS架构场景，每个场景包括架构图、图源代码、生成的CDK基础设施代码以及安全威胁模型和分析。该数据集覆盖了多种AWS部署模式，如无服务器架构、多区域部署、物联网解决方案、机器学习平台和管道、专注于安全的架构、专用计算以及特定行业的解决方案。

The ACSE-Eval Dataset contains AWS deployment scenarios and their threat-models used for determining LLMs threat-modeling capabilities. The dataset consists of over 100 different AWS architecture scenarios, each including architecture diagrams, diagram source code, generated CDK infrastructure code, and security threat models with analysis. The dataset covers a wide range of AWS deployment patterns such as serverless architectures, multi-region deployments, IoT solutions, machine learning platforms and pipelines, security-focused architectures, specialized computing, and industry-specific solutions.