Author

Abdessamad El-Kabid

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Feb 2025

Approaching the Harm of Gradient Attacks While Only Flipping Labels

This work proposes a novel formalization of label flipping attacks as a per-round constrained optimization problem, derives a greedy label-selection rule for logistic regression, and empirically evaluates it beyond its derivation setting, including on MLPs and robust aggregators.

Abdessamad El-Kabid, El-Mahdi El-Mhamdi · arXiv.org · 2 citations