Todd Sundsted @toddsundsted

the tag line for every tech company in 2019: “we blah blah blah blah using data”

(attacks, cont)

Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition

links about attacks:

Explaining and Harnessing Adversarial Examples

Robust Physical-World Attacks on Deep Learning Visual Classification

Note on Attacking Object Detectors with Adversarial Stickers

DARTS: Deceiving Autonomous Cars with Toxic Signs

Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

links about fakes:

Progressive Growing of GANs for Improved Quality, Stability, and Variation

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

AI and Compute

Automated Crowdturfing Attacks and Defenses in Online Review Systems

links to material from my talk at #DragonCon on security weaknesses in artificial intelligence:

first, a stripped-down set of slides:

i'm looking forward to talking about the insecure underside of AI on the EFF track at Dragon Con in two weeks!

aggretsuko is brilliantly funny

gen con in august, dragon con in september, nycc in october. busy next few months...

pothole deep enough to fall into on delancy and allen

another great office game night!

the best writing about artificial intelligence on the web

the challenge of last-mile logistics in a city like NYC

dear god, someone sent me a username/password in an email!

I can’t decide if the problem here is humans, ancient email technology, or something else...

our new kickstarter came this week - el dorado.

superficially i thought it looked like catan, but other than the existence of resources it doesn’t play like catan at all.

enjoying it!