Search Results for author: Kon-Woo Kwon

Found 1 papers, 1 papers with code

ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack

1 code implementation1 Nov 2021 Dahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha Kung

Many prior works on adversarial weight attack require not only the weight parameters, but also the training or test dataset in searching vulnerable bits to be attacked.

Cannot find the paper you are looking for? You can Submit a new open access paper.