Sven Cattell (@comathematician) header
Sven Cattell (@comathematician) profile picture

Founder of @aivillage_dc. Former topologist. I blue team math. 🙂

Joined October 2011
Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)Photo by Sven Cattell (@comathematician)
1) Ok, now that I have a moment I wanna tell some of the story behind this event at @aivillage_dc as I've been working on this for 9 months.
We've been hard at work on the Generative Red Team event we're doing at @defcon for a while and are excited that the @WhiteHouse announced it this morning. Here's more details: aivillage.org/generative%20r…
3
33
8
73
54,887
"Art is made by Humans" was the motto for @aivillage_dc this year. Mathematics is one of the highest forms of art humans make. The beauty is hidden to most, but most mathematicians study it for the art, not the applications. OpenAI doesn't understand this.
1
5
164
This, but for AI Security. The field is filled with people trying to make a quick buck and don't care about the long term health of the field and it's community.
Replying to @ImposeCost
“and your freedom is gone” would be a great way to destroy defcon’s brand and comes off as extreme punishment for a kid throwing sand in a sandbox. However your post does exhibit a commonality with why we have this issue: lack of contextual nuance. We have far too few people in the space willing to culturally guide people towards nuance that’s appropriate for the context of the situation/environment/audience. There are appropriate times for attention grabbing stunts. And its almost always targeting an audience of defenders & resource allocators. And beforehand there should be a deliberate process of understanding how the intended audience will receive it, what they can meaningfully do in response, dynamics of consent, laws, etc etc. People who are new to the space often miss all of that and try to repeat stuff without this nuance. Quick thrills in a world increasingly focused on attention. Even though the action has the tactical equivalent of throwing a brick through a window. Yea… glass can shatter. We all know! Outside of a longer attack chain (and all the other nuance mentioned) it means nothing. Buuuut… new people to the space aren’t often to detailed nuance. Few will read all this. So, for those people, i will just leave a picture of this sticker that someone gave me at defcon:
2
360
Replying to @jakkuh_t
@jakkuh_t I'm the @aivillage_dc founder who bumped into you with the weird hardware stack for a weird application in AI security.
36
The main moat of OpenAI, Google, Anthropic and the rest are the security layers they offer to keep the models behaving as they should. AI security is very difficult and starting with a trusted llm with a solid & agile security team saves businesses money.
2
1
15
845
Meta has some of the best AI risk management infrastructure ever. Fighting spam for 20 years with ML has equipped them for this instance. Use them instead of figuring out it on your own.
2
161
Coding in python feels like spooky action at a distance. You never quite know what you're doing and the documentation is mostly there.
1
1
6
461
I've been in the US for 20 years. We landed 9/11/2004.
3
208
One way to make a QM goon happy is to give them gaffer tape and power strips. AIV had some extra. 😄
2
144
We built a quick landing page in @wix and every part of their site is designed to take your domain hostage. Never use them. #enshittfication
2
5
240
This year's AIV is what I want @aivillage_dc at @defcon to be. Community, connections, and learning is what I want to foster.
Generative Red Team 2 was a massive success. We paid $7350 in bounties. We learnt so much about bounties and reporting for ML. Thank you to everyone who participated!! (specific acks in the thread below)
1
12
1,154
I just spoke to a @hilton @ResortsWorldLV manager about the lock. If hospitality sees a pelican case they will lock your room. Once they're checked by security for guns you *should* be good for the week. This is not part of the extra @defcon sweeps.
1
4
10
1,250
Though, the extra DEFCON sweeps can also trigger a lock until search. The room lock is for guns, and is just standing hotel policy.
2
347
I'm giving a keynote at BsidesLV about the long history of AI risk management and the lessons we keep relearning because parts of this field are terribly documented. I have something cooking to address this which is going to be announced soon. bsideslv.org/talks#keynote-d…
1
6
13
787
Replying to @RideOnewheel
@RideOnewheel People see me riding my one wheel and ask me about it all the time. I tell them "do not buy this, they screw consumers" due to your opposition to right to repair. I still like the ads though. 😁
8
I handed a friend a NVIDIA A6000 GPU at 1 am in an airport parking lot. #defcon
6
186
I have a lot of sympathies for the folks at Crowdstrike, but I look forward to the stickers at @defcon
3
8
44
1,302
Countdowns like these are great at raising my heartrate. 😄
Hacker Fam! We're 28 days away from @defcon- you believe it?! Monday, we'll reveal the #MedicalDevices that will be in our Device Lab. Stay tuned for the excitement and visit villageb.io for the latest updates. See you at DEF CON 32! #defcon #hackers #cybersecurity
3
204
I've been to ~24 security conferences over the last 3 years. I've been to 2 science conferences and got covid at both of them. Be safe people, go to DEF CON and not CVPR!
1
3
305