13 karma · joined November 12, 2020
I've started this project called Plexiglass a while back, which started off as a torch toolbox for adversarial research in DCNNs. I am now rebooting it as a toolbox for testing against adversarial attacks in both DNNs and LLMs.
Idea is to test your DCNNs against adversarial attacks such as fast gradient sign method and toxic prompts in LLMs.
I would very much appreciate contributions, I need more devs as I'm too busy to do this all by myself .
Repo is here: https://github.com/kortex-labs/plexiglass
If you're interested in writing for us, please send us a link of your unpublished draft to our LinkedIn page (https://www.linkedin.com/company/the-ml-practitioner).
Either way, please subscribe to us if you're interested in this kind of content!
Please check it out and would appreciate any feedbacks.. my implementation is far from perfect and I plan on implementing more as my knowledge grows.