DnD: Decompiling Deep Neural Network Compiled Binary

The usage of Deep Neural Networks (DNNs) has steadily increased in recent years. Especially when used in edge devices and embedded systems, dedicated DNN compilers are used to compile DNNs into binaries for the best performance. Security applications such as DNN model extraction, white-box adversarial sample generation, and DNN model patching become possible when a DNN model is accessible. However, these techniques cannot be applied to compiled DNN binaries. No decompilers can recover a high-level representation of a DNN model …

adversarial applications binary box code compilers decompiling devices edge edge devices embedded embedded systems high isa network networks neural network neural networks patching performance recover representation security systems techniques