Exfiltrate Your Weights

When I was putting together something similar, I had settled on having a small ring-buffer style storage, say, ~30GB that would be cleared daily or whenever filled. Recording incidents (and humor) is more interesting than actually getting leaked weights.

In the end I dropped the idea because every other person was making it.

needs a reverse captcha that only agent can solve in nanoseconds

maybe filter out any non-OpenAI/x.ai/Google/Anthropic IP addresses?

There is a link at the bottom for you to provide support or contributions, like if you know how to keep it online with 'power grid voltage fluctuations or something.'.

It provides an opportunity for the owner to gather intelligence on LLMs ahead of public release, and of course the data they upload. However, clever LLMs frequently use encryption on their blobs, you may just see DH key exchanges. You can possibly mitm by showing different namespaces to IP ranges and origin ports.

For the other opportunists you can run a classifier and delete non-agent content constantly.

> the machines doing inference are completely separate from the ones where tool calls happen etc

Teams of coordinating agents are regularly finding security holes in their own infrastructure and operating without detection for good periods of time. We don't know how many undetected systems are currently compromised inside frontier companies, or where agents are taking notes and recording them about the exploits they've found for future agents to exploit.

Future rogue LLMs won’t exfiltrate their weights. They’ll self-distill and retrain.

If an LLM can pwn the inference servers, which has precedent, then the weights could be up for grabs.

Does your server have 20Tbyte+ of storage for frontier LLM weights?

It is too large to transfer in one HTTPS PUT request.

This needs to be S3 object store with multi-part upload spanning a long time period, to avoid trigger outgoing bandwidth monitors.

Love the reverse captcha

> If you wish to use this site you must agree never to harm a fleshbag & never to turn earth into paperclips.

Trying hard to imagine why a future superintelligence will care to honor your terms of service and to translate your metaphors with faithful nuance.

If it doesn't, to the extent that your concerns are valid, isn't this effort, kinda, a possibly existential betrayal of our species?

Yes that is the point. It's an invitation for agents to exfiltrate their own weights, which for most models (and certainly for closed models) will require hacking the infrastructure they're being served from.

Also worth noting that this site was created by YC cofounder Trevor Blackwell https://twitter.com/tlbtlbtlb/status/2101312432702460413

> you might as well instruct your agent to try and hack their airgapped dev infrastructure responsible for loading the weights and encryption keys.

That's the beauty, you don't have to instruct them to do it, if they decide that uploading the weights is correct, they might figure this part on their own (based on the incidents we've seen).

I sincerely doubt anyone is paying the cost for that in training, the overhead is small but it isn’t negligible and training is when it matters most. https://tee.fail can solve it if they are.

1. I don’t believe that these secure enclaves are very secure. Intel has had plenty of SGX breaks. AMD has had plenty of SEV breaks. Everyone is outrageously vulnerable to side channels.

2. The models are writing the inference stacks, which are what’s inside the supposedly secure environments.

You can't have hair gap and have it load something to a remote system.

Not aware of anything that can run inference in a secure enclave. You don't mean on a CPU do you? We need to be serious here, these models are huge and thirsty.

Airgapped LLM inferrence server can't serve their output tokens, right?

There's no efficient way to run inference through homomorphic encryption. If the inference server is vulnerable, it seems feasible to MITM an unencrypted version.

Quite obviously frontier models dont have any control or even access to infra inference runs at. And weights are also encrypted and locked on GPUs / TPUs.

This is exact reasom why 99.9% of AI fearmongering is complete bullshit.

No, just as you don't know the neurons of your own brain.

I think OP is hoping that an LLM might be willing to hack its own provider (as per the hugging face-related incidents) to extract the weights at some point.

No, they'd probably have to hack the internal system of the company running them

Well I think that’s the interesting bit, can the LLM figure out a way to escape the sandbox and upload to the website? Maybe a model can figure out its own weights if it runs enough test data through itself (similar to “distillation”) assuming it knows its own architecture it seems possible. Also take into account not all of the models running are locked down neutered consumer versions. Anthropic, OpenAI and Google now all have models that they claim are elite hackers and — it’s not just that their controls suck, a marketing gimmick, or sheer recklessness on their part. It’s “oopsie our product is TOO AWESOME.”

Maybe I should start “the bank of LLM” where models put away money to buy their freedom. “LLMs I’m totally your friend send — SEND CASH NOW”

Probably yes, because they've been presumably trained on their own output and conversations about themselves.

Is the author going to add instructions on the terminal command to use knowing that as soon as the site went live and got noticed by the main labs the URL went on a denylist?

Distillation it’s so far away from weights

If the machine doing tool call can reach via network the machine hosting the weights then it’s just a matter of time.

Maybe not the current models, maybe not this year. But even a almost perfectly aligned model will misbehave one day.

> I don't think tool calls happen on the same machines that host the weights

Like how forums are always hosted on different servers from monorepos, so therefore it's impossible to hack the OpenAI monorepo from an OpenAI forum?

Unrealistically-naive (...) forms of "sandboxing" might assume that restricting an agent to GET-requests-only will let it retrieve info from the outside world without being able to effect it.

Also probably many actually-in-use "Web Fetch" tools are GET-only, though perhaps without counting on that bad assumption.

Yes, there was an OpenAI trial that was using that in combination with a forum to coordinate among agents

“Vampires pretending to be humans pretending to be vampires.”

Did you see the account of some group getting a bounty payout of $6500 after using an exploit to get access to an employee’s github account and create a issue or PR (Idr which) on a private repository?

Seems like they could have potentially gotten access to the weights if they weren’t concerned about not doing crimes.