-
Notifications
You must be signed in to change notification settings - Fork 9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[FEATURE] New notebook for detecting python code vulnerabilities using GPT4 #1100
Comments
This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 10 days. |
Commenting so this issue stays open. Can maintainers take a look at the notebook in #1112 and let me know if it can be merged or not? Thank you. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is there any interest in a notebook contribution that demonstrates a few ways of prompting GPT4 to detect insecure code snippets? The solution would include prompt templates that use techniques like few-shot learning, KNN-based few-shot learning (from this paper), and asking for a code fix (proposed by this paper) to increase prediction accuracy.
Is your feature request related to a problem? Please describe.
This is a proposal for a new use case. It would help users who are looking for examples that:
Describe the solution you'd like
I've written a draft notebook based on my experiments and would be happy to submit a PR. I'm an experienced software engineer and have recently been applying AI to topics in software security.
Additional context
There would be a new data file based on the published dataset from this paper which has this license. The notebook would cite all sources and include some evaluation metrics. Thanks for your consideration.
The text was updated successfully, but these errors were encountered: