Supporting Software Engineers in IT Security and Privacy through Automated Knowledge Discovery - Dataset

<h1>Supporting Software Engineers in IT Security and Privacy through Automated Knowledge Discovery - Dataset</h1> <h2>&nbsp;</h2> <h2>Dataset corresponding to&nbsp;<a href="https://doi.org/10.1145/3672608.3707798">https://doi.org/10.1145/3672608.3707798</a></h2> <div>This is the dataset corresponding to&nbsp;<a href="https://doi.org/10.1145/3672608.3707798">https://doi.org/10.1145/3672608.3707798</a> "Supporting Software Engineers in IT Security and Privacy through Automated Knowledge Discovery" with the goal of providing a systematic method to discover state-of-the-art security knowledge, focused on threats, measures, and properties from science and project literature with minimal manual effort, and providing software engineers with the awareness and means they need to apply the knowledge to their projects.</div> <p>&nbsp;</p> <h2>Structure of the files</h2> <div>The dataset contains the extraction prompt, the extraction results, and metadata.</div> <div>- <strong>ACM_IEEE_EU_Results.zip</strong> is an archive file with the metadata and extraction results with the following folder structure:&nbsp;</div> <div>&nbsp; &nbsp; - <strong>Meta/ </strong>contains the DOI, title, publication date, and pages (omitted for IEEE since it may contain intellectual property).</div> <div>&nbsp; &nbsp; - <strong>Extract/</strong> contains extraction results generated by the LLM in response to the extraction_prompt.txt file.</div> <div>&nbsp; &nbsp; - <strong>ExtractMeta/</strong> contains the metadata for the extraction, such as execution time.</div> <div>- <strong>extraction_prompt.txt</strong> is the prompt used to extract information from the science and project publications.</div>