Hacker News new | past | comments | ask | show | jobs | submit login

What if "共匪" is presented graphically? Do the sniffers have the image recognition to flag those too?



Generic corporate spam filters can OCR for spam text in pictures and have been able to do that for many years, I would assume Google can too.


Very interesting. I wonder what would happen if you put in some special noise from adversarial AI methods today. Would be a real arms race of detection vs evasion.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: