Alfredo Ortega <ortegaalfr...@gmail.com> writes: > Hi! Sorry if this is not the appropriate list to share openbsd-related > projects (perhaps it was misc?) > > I want to inform you about this project about using LLMs to inject > thousands of security checks into the OpenBSD kernel automatically. > > I'm sharing the first results at > https://github.com/ortegaalfredo/openbsd-hardcore , where I used the > automated tool to add thousands of additional security checks to the > netinet/netinet6 stack of kernel 7.5. My plan is to continue this > process with other subsystems, which will be largely automated, and to > improve the tool so it can be used in other projects. The tool is not > yet public but the idea is quite simple and can be implemented easily. > This is a demonstration of the capabilities of LLMs as a > code-refactoring tool.
I had an idea in this space which should have a much better ROI and chances of acceptance. I'd start by grabbing a syzkaller report from https://syzkaller.appspot.com/openbsd. Ideally you want something with a reproducer. You should probably verify the repro still works. Then feed whatever data you find relevant into the magic box and ask it to give you a fix for the problem. Some relevant pieces would include the panic stack trace and the code around it. Since you know it is a real problem and have a way to verify the proposed solution, people will take you more seriously. When you have the first real fix - do let us know, I'll personally be very excited to look at the patches. Thanks Greg P.S. As much as I'd love for you to focus on OpenBSD, you'll find many more bugs to fix in other systems there.