Viewing profile — jackcook

Thanks for reading! The two stories are of course deeply intertwined: we wouldn’t have found the new side channel without the cautionary tale about machine learning. But the findin…

Websites doing this would have to be careful about it: they might become the only website triggering a lot of interrupts randomly, which then makes them easy to identify. Our count…

Thank you! Really appreciate it

Yes you're spot on, the nonlinearities come from the full Mamba blocks, which I left out of this post for simplicity/to focus on the bigger ideas the paper introduced. You can see …

Thank you for the kind words! I think it’s mostly to reduce complexity during training. Here’s an excerpt from page 9 of the Mamba paper: “We remark that while the A parameter coul…

Wow, it was quite the surprise to wake up to seeing this post near the top of HN! I wrote the post, happy to answer questions if anyone is wondering about any details.

Yes, you're right, I should have mentioned it in the post, but I used pure greedy sampling for the GPT-2 outputs since I couldn't do anything but that for the Apple model. So tempe…

I used greedy sampling (temperature 0) for all of them. Since I didn't have access to logits/probabilities for Apple's model, I wasn't able to do anything else in a way that would …

Some context: In the upcoming versions of macOS and iOS, Apple is including a predictive text model which offers suggestions while you type, which they’ve said to be a "transformer…

Apple is including a predictive text model which offers suggestions while you type, which they’ve said to be a "transformer model". I managed to find some details about this model

I got a warning today when submitting my app that said I was using a private API function. Turns out they've essentially blacklisted certain function names that match anything in o…

I don't think any of these side channels are really easy to pull off without the technical capabilities of a nation state or something similar. I personally think embedding a malic…

You'd just need to put the script on any webpage the user might access and leave open, such as Google, or Facebook, or whatever. The attack isn't specific to JavaScript, so really …

You can pull off attacks like this from JavaScript by repeatedly recording the time and training a machine learning model on traces of instruction throughput over time, which my gr…