Abstract: A generative AI based pipeline has been created that ranks generated responses that are candidate software patches. The ranking is based on predicted quality measures of code fragments within a corresponding prompt to a generated AI model. The predicted quality measures are generated by a machine learning model that has been trained based on features that are values/measures of similarity metrics between code fragments, between code fragment changes, between code structures, and/or between changes of code structures.

Abstract: A generative artificial intelligence (AI) driven code fixing pipeline has been created that uses a large language model (LLM) to recommend fixes for vulnerabilities detected in program code. A scanner generates indications of flaws in program code and weakness types for those flaws. One or more example code pairs are retrieved based on weakness type and programming language, an example code pair including an example flaw and an example fix of that flaw. The LLM is then prompted with a code fragment corresponding to a detected vulnerability, context for the code fragment, and the one or more example code pairs to generate a modification of existing program code that fixes the vulnerability.

Abstract: A generative artificial intelligence (AI) driven code fixing pipeline has been created that uses a transformer-based large language model (LLM) to patch flawed program code. A pre-trained LLM is fine-tuned to generate a response that is a modified version of a code fragment in a prompt to the pre-trained model. After fine-tuning, the pre-trained LLM (hereinafter “code fix model”) is integrated into a pipeline that includes a program code cybersecurity scanner and a prompt generator. The scanner generates indications of flaws in program code and weakness types for those flaws. These indications flow into the prompt generator. The prompt generator retrieves reference code pairs based on weakness type and programming language to generate a batch of prompts to run inference on with the code fix model. The responses generated by the code fix model are presented as patching alternatives.

Abstract: A generative AI based pipeline has been created that ranks generated responses that are candidate software patches. The ranking is based on predicted quality measures of code fragments within a corresponding prompt to a generated AI model. The predicted quality measures are generated by a machine learning model that has been trained based on features that are values/measures of similarity metrics between code fragments, between code fragment changes, between code structures, and/or between changes of code structures.

Abstract: A generative artificial intelligence (AI) driven code fixing pipeline has been created that uses a transformer-based large language model (LLM) to patch flawed program code. A pre-trained LLM is fine-tuned to generate a response that is a modified version of a code fragment in a prompt to the pre-trained model. After fine-tuning, the pre-trained LLM (hereinafter “code fix model”) is integrated into a pipeline that includes a program code cybersecurity scanner and a prompt generator. The scanner generates indications of flaws in program code and weakness types for those flaws. These indications flow into the prompt generator. The prompt generator retrieves reference code pairs based on weakness type and programming language to generate a batch of prompts to run inference on with the code fix model. The responses generated by the code fix model are presented as patching alternatives.