Publications

Odelia Melamed, Gilad Yehudai, Gal Vardi
January, 2025 arXiv preprint arXiv:2510.14844
Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks
PDF Cite
Odelia Melamed, Gilad Yehudai, Adi Shamir
January, 2024 Advances in Neural Information Processing Systems, 37
MALT Powers Up Adversarial Attacks
PDF Cite GitHub Project Conference Page
Odelia Melamed, Rich Caruana
January, 2023 in NeurIPS Explainability workshop XAIA 2023
Explaining high-dimensional text classifiers
PDF Cite Conference Page
Odelia Melamed, Gilad Yehudai, Gal Vardi
January, 2023 Advances in Neural Information Processing Systems, 36
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
PDF Cite GitHub Project Conference Page
Adi Shamir, Odelia Melamed, Oriel BenShmuel
January, 2021 arXiv preprint arXiv:2106.10151
The dimpled manifold model of adversarial examples in machine learning
PDF Cite