Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Could the return strings be generated by a Deep Learning powered fuzzer?


The return strings could be anything, provided they fall under the max length in the spec. DP fuzz it all you want.


What are you trying to achieve?


He's trying to crash a script-kiddy's box with fuzzing. It's a fun thought, though I'm not sure it's practical as you'd only get a few tries. Fuzzing is typically an approach of throwing it the wall and seeing what sticks; if your deep learning found something that crashed most ssh clients that would just be a zero-day.


Maybe deep learning technobabble that might convince a script kiddie into "researching" what was coming back?


It doesn't have to crash them all...just the one it's working on.


Stickier tar.




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

Search: