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

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

sf/berlin/seattle
Joined June 2011
Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by Ian Klatzco (@ian5v)Photo by 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.
1
1
161
I'm particularly interested in the new-ish secure enclave feature, "NVIDIA Confidential Compute".
2
116
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)
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
279
Ian Klatzco retweeted
Good day to remember just how big that green tree is
290
6,416
493
58,112
4,068,852
USENIX Security ML / AI Track
1
3
494
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
166
identifying unsafe content using vision language models
2
1
116
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