This is interesting! Can’t you just filter this range of unicode characters out of your apps input before it hits the model? Most models aren’t exposed to users as direct inference, it’s wrapped in an application. I guess there’s some implication for data poisoning, but realistically datasets should be fed through similar filtering to look for adversarial inputs.
@joseph_thacker
8 ай бұрын
Yes, but that's like saying "all apps should sanitize user input against xss and sanitize sql queries against injection". I've been doing bug bounty hacking for more than 4 years with over 1000 reports. Most companies still struggle to do those 2 things well. This issue feels like a simialr problem. Every app developer has to fix it. I'd rather scrub the training data of any unicode tags so future models don't even understand them. There's very little use.
@endlessvoid7952
8 ай бұрын
@@joseph_thackervery true, just because it should be filtered doesn’t mean everyone will do it or even be aware that they need to 😢
@pmolax5903
8 ай бұрын
I enjoyed it
@Mr_tadoo
9 ай бұрын
it was interesting, Tnx.
@_0x01m
10 ай бұрын
can you share the wordlists that your using during vhost fuzzing? Thank you for your content.
@omarataallah9451
Жыл бұрын
what discord server is this ? and thanks for these great info
@cair0_
2 жыл бұрын
I donn no y i had to C thi5
@xettabyte1
2 жыл бұрын
can i have the slide?
@feedonomics8103
2 жыл бұрын
This is nice ,my noob brains is strugling with those scripts!🥴
@noobsploit3103
2 жыл бұрын
Full smupport
@raanonyms7926
3 жыл бұрын
11:34 ssrf - fuzzing, interesting !
@N1n35-42
3 жыл бұрын
What happened on 6:03 ?
@joseph_thacker
3 жыл бұрын
d0nut was recording it. I think he accidentally turned it down for about 20 seconds.
@shubham_srt
2 жыл бұрын
noise reduction, just as he is explaining in the slides 😂😂
Пікірлер