TY - DATA T1 - Code for the publication "Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm" PY - 2025/05/19 AU - Yanqi Qiao AU - Dazhuang Liu UR - DO - 10.4121/1753c8aa-adf4-4256-ae74-02e34ba120cf.v1 KW - backdoor attack KW - computer vision KW - black-box KW - frequency domain KW - simulated annealing KW - robustness N2 -
This research aims to investigate the vulnerabilities of existing convolutional neural networks (CNNs) and vision transformers (ViTs) against backdoor attacks and to develop a novel backdooring approach. The study focuses on advancing a new technology in this area. The research uses textual data, with all data (i.e., source code) being independently developed.
ER -