Live data from Hacker News

U of T researchers demonstrate AI worm could target any online device

utoronto.ca

1–10 of 53 posts

Re: U of T researchers demonstrate AI worm could target any online device

#4
post #3

The academic paper is here: https://arxiv.org/abs/2606.03811 It's not fully described how things work exactly, but apparently it does not transfer entire LLMs as part of the worm. Now that would be interesting :)

In the abstract, what does it mean "the attacker's marginal cost per new infection is zero"?

Re: U of T researchers demonstrate AI worm could target any online device

#6
post #3

The academic paper is here: https://arxiv.org/abs/2606.03811 It's not fully described how things work exactly, but apparently it does not transfer entire LLMs as part of the worm. Now that would be interesting :)

In the abstract, what does it mean "the attacker's marginal cost per new infection is zero"?

If you infect a machine with GPU enough to run the localLLM needed to steal another machine, you can let it burn tokens all day for free because whoever you stole the first one from will pay the electric bill.

Re: U of T researchers demonstrate AI worm could target any online device

#7
Did people doubt that this was theoretically possible? Seems self-evident to me. The interesting thing will be seeing it in the real world rather than in a controlled environment where they deliberately made all devices on the network have a known vulnerability.

Re: U of T researchers demonstrate AI worm could target any online device

#9
post #7

Did people doubt that this was theoretically possible? Seems self-evident to me. The interesting thing will be seeing it in the real world rather than in a controlled environment where they deliberately made all devices on the network have a known vulnerability.

[dead]
Post reply on HN