International Journal of Machine Learning and Cybernetics · 2021 · Journal article

Backdoor learning curves: explaining backdoor poisoning beyond influence functions

Antonio Emanuele Ciná, Kathrin Grosse, Sebastiano Vascon, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo

University of Genoa · École Polytechnique Fédérale de Lausanne · Ca' Foscari University of Venice · University of Cagliari

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2024-09-26
Citations
11
arXiv
2106.07214
Cite
@article{cin2021backdoor,
  title = {Backdoor learning curves: explaining backdoor poisoning beyond influence functions},
  author = {Antonio Emanuele Ciná and Kathrin Grosse and Sebastiano Vascon and Ambra Demontis and Battista Biggio and Fabio Roli and Marcello Pelillo},
  year = {2021},
  journal = {International Journal of Machine Learning and Cybernetics},
  eprint = {2106.07214},
  archivePrefix = {arXiv},
  doi = {10.1007/s13042-024-02363-5},
  url = {https://arxiv.org/abs/2106.07214},
}