lqdev🦫

https://arxiv.org/pdf/2210.00108.pdf

...backdoors can be added during compilation, circumventing any safeguards in the data preparation and model training stages.

some backdoors, such as ImpNet, can only be reliably detected at the stage where they are inserted and removing them anywhere else presents a significant challenge.

machine-learning model security requires assurance of provenance along the entire technical pipeline, including the data, model architecture, compiler, and hardware specification.


Send me a webmention
Back to feed