Ian Klatzco (@ian5v) header
Ian Klatzco (@ian5v) profile picture

Ian Klatzco

@ian5v

hacker 馃尃 @sigpwny prev: @leviathansec and @SPR_Illinois 馃https://xitter.gq/t.co/QcaBtdqIkN

 sf/berlin/seattle
klatz.co
Joined June 2011
  • Tweets1.9K
  • Following561
  • Followers567
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.
1
1
168
I'm particularly interested in the new-ish secure enclave feature, "NVIDIA Confidential Compute".
2
122
update: they enable you to know that the request you're seeing Now was signed by the same secure element you saw Earlier. (now, there is also syncing between devices in an eg apple/google ecosystem)
Ian Klatzco (@ian5v) profile pictureIan Klatzco@ian5v17 Jun 2024
why on earth are passkeys better? they seem harder to understand. the only benefit seems to be that the sign-in flow is slightly smoother in some cases.
1
284
Ian Klatzco retweeted
Tim Urban (@waitbutwhy) profile picture
Tim Urban
@waitbutwhy1 Jan 2025
Good day to remember just how big that green tree is
Image from Tim Urban (@waitbutwhy)
290
6,413
493
58,016
4,069,024
USENIX Security ML / AI Track
Image from Ian Klatzco (@ian5v)
1
3
496
more replies
Image from Ian Klatzco (@ian5v)
1
156
sdv3 might be a transformer (cf sdv2 which is a vae+unet)
112
usenix dot org really needs to put the papers in a cdn....
1
171
identifying unsafe content using vision language models
Image from Ian Klatzco (@ian5v)
2
1
117
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
55
Load more