Jump to content

Veracode, Inc. (20250004915). GENERATIVE ARTIFICIAL INTELLIGENCE DRIVEN SOFTWARE FIXING

From WikiPatents
Revision as of 02:54, 25 March 2025 by Unknown user (talk) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

GENERATIVE ARTIFICIAL INTELLIGENCE DRIVEN SOFTWARE FIXING

Organization Name

Veracode, Inc.

Inventor(s)

Roman Rudenko of Vienna AT

Anna Bacher of Vienna AT

GENERATIVE ARTIFICIAL INTELLIGENCE DRIVEN SOFTWARE FIXING

This abstract first appeared for US patent application 20250004915 titled 'GENERATIVE ARTIFICIAL INTELLIGENCE DRIVEN SOFTWARE FIXING

Original Abstract Submitted

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.

(Ad) Transform your business with AI in minutes, not months

Custom AI strategy tailored to your specific industry needs
Step-by-step implementation with measurable ROI
5-minute setup that requires zero technical skills
Get your AI playbook

Trusted by 1,000+ companies worldwide

Cookies help us deliver our services. By using our services, you agree to our use of cookies.