Home

Awesome

Black-box-Adversarial-Reprogramming

This is the repo for Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho, in Proceeding of International Conference on Machine Learning (ICML), 2020. Our code is implemented in Python 3.6 and Tensorflow 1.14.

The following figure illustrates the framework for our proposed black-box adversarial reprogramming method (BAR): <br/> Alt text<br/> <br/>

  1. Generate adversarial program. <br/>

  2. Find q pertubed adversarial programs with vectors that are uniformly drawn at random from a unit Euclidean sphere. <br/>

  3. Estimate gradient with zeroth-order gradient estimator. The corresponding algorithmic convergence guarantees have been proved in both the convex loss and non-convex loss settings (Liu et al., 2018; 2019).<br/>

  4. Optimize adversarial program’s parameters W. <br/>

For more detail, please refer to our main paper, and video on slideslive!.