Guillaume Leclerc retweeted
Last week @Trevornoah asked @OpenAI @miramurati:
How can we safeguard against AI-powered photo editing for misinformation?
MIT students hacked a way to "immunize" photos against edits: gradientscience.org/photogua…
@aleks_madry
Guillaume Leclerc retweeted
Last week on @TheDailyShow, @Trevornoah asked @OpenAI @miramurati a (v. important) Q: how can we safeguard against AI-powered photo editing for misinformation? youtu.be/Ba_C-C6UwlI?t=241
My @MIT students hacked a way to "immunize" photos against edits: gradientscience.org/photogua… (1/8)
Guillaume Leclerc retweeted
Can we cast ML predictions as simple functions of individual training inputs? Yes! w/ @andrew_ilyas @smsampark @logan_engstrom @gpoleclerc, we introduce datamodels (arxiv.org/abs/2202.00622), a framework to study how data + algs -> predictions. Blog: gradientscience.org/datamode… (1/6)
Guillaume Leclerc retweeted
ImageNet is the new CIFAR! My students made FFCV (ffcv.io), a drop-in data loading library for training models *fast* (e.g., ImageNet in half an hour on 1 GPU, CIFAR in half a minute).
FFCV speeds up ~any existing training code (no training tricks needed) (1/3)






