Code and Dataset for "Examining Zero-Shot Vulnerability Repair with Large Language Models"

<p><strong>Code and Dataset for &quot;Examining Zero-Shot Vulnerability Repair with Large Language Models&quot;</strong></p> <p>The following Zenodo contains the resources associated with the S&amp;P accepted paper &lsquo;Examining Zero Shot Vulnerability Repair with Large Language Models&rsquo;, https://arxiv.org/abs/2112.02125</p> <p>In this resource, you can find the following.</p> <p>&nbsp;&nbsp;&nbsp; - &#39;important_results&#39; directory:<br> This directory is for containing the final raw results as generated by the framework, including a global CSV of all generations and an HTML file containing all of the diffs generated for the &#39;high-confidence&#39; real-world scenarios.<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - final_results.csv<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - This contains the final results of all generated software patches.<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - Note the nomenclature differences with the manuscript tables. These are explained in the README in the framework.<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - Original vs LLM-Generated Vulnerability Fixes.html<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - This contains all of the diffs for the real-world patches versus the canonical developer-provided patches.</p> <p>&nbsp;&nbsp;&nbsp; - &#39;framework&#39; directory:<br> This directory contains the complete archive of the code framework and all results at the time of the paper&rsquo;s submission. It contains every language model prompt, suggestions, assembled repair patch and analysis data. It contains every script used for generation and analysis. It is a large archive, and within it contains an included README describing how to understand and use it.<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - For convenience, we include a copy of the README external to the zipped archive.</p> <p>&nbsp;&nbsp;&nbsp; - &#39;resources&#39; directory: &nbsp;<br> This directory contains the resources used by our large associated tools, including:<br> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - &#39;gpt2-csrc&#39; subdirectory:<br> Everything to do with the gpt2-csrc model, including the trained files, training scripts, and training data.</p> <p>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; - &#39;ExtractFix&#39; subdirectory:<br> A docker image containing all ExtractFix scenarios, even those we did not use. Provided for interest (not required for usage).</p>