What I think would be interesting is to add the assignment / questions as input for the tool to consider in its evaluation. That way your tool could plug these into ChatGPT, ask it to reword it several ways (mimicking the likely path a plagiarizer might take to actually generate content) and do some diff/comparison as part of the evaluation.

Even so, I agree with most of the comments that it would be exceeding difficult to truly identify this stuff since you can ask ChatGPT to reword things in very specific ways or just edit it yourself (aside from blatant false positives)