Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search
Paper summary Rakin et al. introduce the bit-flip attack aimed to degrade a network’s performance by flipping a few weight bits. On Cifar10 and ImageNet, common architectures such as ResNets or AlexNet are quantized into 8 bits per weight value (or fewer). Then, on a subset of the validation set, gradients with respect to the training loss are computed and in each layer, bits are selected based on their gradient value. Afterwards, the layer which incurs the maximum increase in training loss is selected. This way, a network’s performance can be degraded to chance level with as few as 17 flipped bits (on ImageNet, using AlexNet). Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
arxiv.org
scholar.google.com
Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search
Rakin, Adnan Siraj and He, Zhezhi and Fan, Deliang
arXiv e-Print archive - 2019 via Local Bibsonomy
Keywords: dblp


[link]
Summary by David Stutz 4 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and