Adversarial Reprogramming of Neural Cellular Automata
Abstract
Distill articles are interactive publications and do not include traditional abstracts. This summary was written for the ML Anthology. Demonstrates that trained neural cellular automata can be adversarially reprogrammed to perform novel tasks or produce incorrect outputs, exploring the robustness of learned self-organizing behaviors.
Cite
Text
Randazzo et al. "Adversarial Reprogramming of Neural Cellular Automata." Distill, 2021. doi:10.23915/distill.00027.004Markdown
[Randazzo et al. "Adversarial Reprogramming of Neural Cellular Automata." Distill, 2021.](https://mlanthology.org/distill/2021/randazzo2021distill-adversarial/) doi:10.23915/distill.00027.004BibTeX
@article{randazzo2021distill-adversarial,
title = {{Adversarial Reprogramming of Neural Cellular Automata}},
author = {Randazzo, Ettore and Mordvintsev, Alexander and Niklasson, Eyvind and Levin, Michael},
journal = {Distill},
year = {2021},
doi = {10.23915/distill.00027.004},
url = {https://mlanthology.org/distill/2021/randazzo2021distill-adversarial/}
}