Ian Klatzco

1.9K posts

Ian Klatzco banner
Ian Klatzco

Ian Klatzco

@ian5v

hacker 🌠 @sigpwny prev: @leviathansec and @SPR_Illinois 🦋https://t.co/QcaBtdqIkN

sf/berlin/seattle Katılım Haziran 2011
558 Takip Edilen569 Takipçiler
Ian Klatzco
Ian Klatzco@ian5v·
@richinseattle I'm particularly interested in the new-ish secure enclave feature, "NVIDIA Confidential Compute".
English
0
0
2
72
Ian Klatzco
Ian Klatzco@ian5v·
Hey @richinseattle! Thanks again for your Toorcamp talk last year, I really enjoyed getting curious about e.g. why .safetensors is "safer" than .pickle. Do you know anyone who is really into GPU security? I've been curious about their fuzzability for a while.
English
1
0
1
111
Ian Klatzco retweetledi
Tim Urban
Tim Urban@waitbutwhy·
Good day to remember just how big that green tree is
Tim Urban tweet media
English
299
6.6K
59.2K
4.1M
Taro@PROJEKT GODHAND 1.0 OUT NOW
it's definitely impossible, but how hard would it actually, seriously be for someone with a ton of money and some technical knowhow to make their own payment processor? like what are the genuine "risks and challenges" (earnest question) there's clearly money to be made there...
English
3
0
22
1.2K
Ian Klatzco
Ian Klatzco@ian5v·
sdv3 might be a transformer (cf sdv2 which is a vae+unet)
Português
0
0
0
107
Ian Klatzco
Ian Klatzco@ian5v·
USENIX Security ML / AI Track
Ian Klatzco tweet media
English
1
0
3
476
Ian Klatzco
Ian Klatzco@ian5v·
usenix dot org really needs to put the papers in a cdn....
English
0
0
1
150
Ian Klatzco
Ian Klatzco@ian5v·
input: manually labeled dataset of unsafe concepts (gun violence, banned flags, sexual harassment)... result/contribution: UnsafeConcepts dataset of 75 concepts / 1500 images in 9 categories
English
0
0
0
54
Ian Klatzco
Ian Klatzco@ian5v·
identifying unsafe content using vision language models
Ian Klatzco tweet media
English
2
0
1
115