[Two_hands]

Yeah tbh I do recommend using this alongside a privacy screen for best protection. Privacy screens also suffer from the fact that they won’t block someone directly behind you from seeing the screen, so both methods have issues.

Any tips on improving accuracy? A lot of it might be due to lack of diverse images + labelling errors as I did it all manually.

[IshKebab]

I dunno, my only idea is that maybe if you use traditional face detection to find the face/eyes and then do classification (assuming you aren't doing that already?).

[Two_hands]

Right now that's pretty much what I do. I use YuNet to get faces, crop them out and run detection. It's probably a factor of a not enough data/poor model choice.