News for hackers. Stuff that matters.
Re:An image preprocessing tool to protect artworks from AI-f... by LeftHandPath on Thursday August 24, 2023 @08:43PM (#37256434)
This is incredibly similar to a paper one of my professors was working on a year or two ago: [0]

> Neural Trojans embedded in pre-trained neural networks are a harmful attack against the DNN model supply chain. They generate false outputs when certain stealthy triggers appear in the inputs. While data-poisoning attacks have been well studied in the literature, code-poisoning and model-poisoning backdoors only start to attract attention until recently.

While I agree with other commenters here that it's hard to imagine it being widely implemented at the moment, I think it's only the beginning of this type of tech. In a few years, maybe this type of data poisoning could be as ubiquitous as SSL and as subtle as webp compression artifacting.

[0]: https://dl.acm.org/doi/abs/10.1145/3548606.3560678

There are no comments on this comment yet.