no code implementations • 12 Sep 2023 • Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan, Sihang Hu, Tianxiang Li, Shuai Wang
Nevertheless, we find that DNN executables contain extensive, severe (e. g., single-bit flip), and transferrable attack surfaces that are not present in high-level DNN models and can be exploited to deplete full model intelligence and control output labels.
no code implementations • 3 Oct 2022 • Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma
BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models.
no code implementations • 31 Jan 2020 • Zhibo Liu, Feng Gao, Yizhou Wang
We present a method for improving human design of chairs.