Explore a groundbreaking 24-minute Black Hat conference talk on BTD (Bin to DNN), a decompiler for deep neural network (DNN) executables. Delve into the world of deep learning models compiled into executables for heterogeneous hardware devices. Discover how BTD leverages low-level hardware primitives to enable efficient DL computations across various computing platforms, including CPUs, GPUs, and hardware accelerators. Learn about the innovative approach presented by researchers Tianxiang Li, Wenqiang Li, Zhibo Liu, Shuai Wang, Xiaofei Xie, and Yuanyuan Yuan to decompile DNN executables, potentially revolutionizing the field of deep learning and cybersecurity.
Unleashing the Power of Decompilation for x86 Deep Neural Network Executables
Overview
Syllabus
BTD: Unleashing the Power of Decompilation for x86 Deep Neural Network Executables
Taught by
Black Hat
Related Courses
-
Decompiling Deep Neural Network Compiled Binary
-
Habitat - A Runtime-Based Computational Performance Predictor for Deep Neural Network Training
-
Deep Neural Networks for Hackers - Methods, Applications, and Open Source Tools
-
Deep Learning on Disassembly
-
Effectively Scheduling Computational Graphs of Deep Neural Networks toward Their Domain-Specific Accelerators
-
An AI Approach to Malware Similarity Analysis - Mapping the Malware Genome With a Deep Neural Network
