CarperAI / InstructGPT

For experiments involving instruct gpt. Currently used for documenting open research questions.
MIT License
71 stars 3 forks source link

[task] Security Vulnerability Detection #17

Open jon-tow opened 1 year ago

jon-tow commented 1 year ago

🚀 The Task

Given source code with (potential) security vulnerabilities, the model should be able to detect and discuss the issue with the programmer.

Example

<user> Is there any issue with this code? 
  {code that can be attacked through buffer overflow}
<instruct> Yes, the array can be used for a buffer overflow attack
<user> Is it dangerous?
<instruct> Yes it allows for arbitrary code execution

Additional Notes

jon-tow commented 1 year ago

Related Issue: #6