EvilModel: Hiding Malware Inside of Neural Network Models [pdf]

Re:EvilModel: Hiding Malware Inside of Neural Network Models... by joosters on Tuesday July 20, 2021 @08:10AM (#27892773)

Maybe because of the density of the payload? Hiding 37MB of data inside of 178MB of images would not be possible without severely degrading the image quality - and they are simple to check. Whereas the NN model continued to work with very little quality loss.

(You could easily append 37MB of hidden data to some images - e.g. adding an invisible extra layer to the image, but this paper details a technique where you don't alter the file size)

[ Parent | on HN ]

Re:EvilModel: Hiding Malware Inside of Neural Network Models... by mirker on Tuesday July 20, 2021 @08:20AM (#27892868)

They use AlexNet, which is way out of date at this point and I believe understood to be parameter inefficient. Most of those model parameters are likely useless, and at least less useful than those of other newer models. The model they chose is basically zero-padded and they are appending to the zero-d region.

Also, the newest JPEG standard is nearly Turing complete, so you can possibly compress the data into a program which is the same size as the Kolmogorov complexity of the data.

[ Parent | on HN ]

Re:EvilModel: Hiding Malware Inside of Neural Network Models... by high_byte on Tuesday July 20, 2021 @08:22AM (#27892888)

not true. 178mb bmp could become few mb of jpg, even kb for mspaint quality images (ie. few colors, low frequency)

[ Parent | on HN ]