Trustworthy DD · Kernel and closed-form inner solvers
Can we achieve robustness from data alone?
Nikolaos Tsilivis, Jingtong Su, Julia Kempe
ICML 2022 Workshop · first public 2022-07-24 · arXiv 2207.11727
In one paragraph
Poses adversarially robust classification as a bi-level kernel-ridge-regression problem over Neural Tangent Kernels, optimizing a dataset once so that plain gradient descent on it yields a robust model with no specialized robust training algorithm. The paper reports experiments across standard vision benchmarks and models, and revisits a prior data-optimization approach to argue that robustness from standard training on an optimized dataset is harder to obtain than previously claimed.
Where it sits
- Kernel and closed-form inner solvers (Bi-level performance matching)
- Setting: Image classification
Design choices
| Optimization regime | bilevel |
| Prior / networks used | ntk-kernel |
Abstract (verbatim from arXiv)
We introduce a meta-learning algorithm for adversarially robust classification. The proposed method tries to be as model agnostic as possible and optimizes a dataset prior to its deployment in a machine learning system, aiming to effectively erase its non-robust features. Once the dataset has been created, in principle no specialized algorithm (besides standard gradient descent) is needed to train a robust model. We formulate the data optimization procedure as a bi-level optimization problem on kernel regression, with a class of kernels that describe infinitely wide neural nets (Neural Tangent Kernels). We present extensive experiments on standard computer vision benchmarks using a variety of different models, demonstrating the effectiveness of our method, while also pointing out its current shortcomings. In parallel, we revisit prior work that also focused on the problem of data optimization for robust classification \citep{Ily+19}, and show that being robust to adversarial attacks after standard (gradient descent) training on a suitable dataset is more challenging than previously thought.
BibTeX (generated; prefer the venue's official entry)
@article{tsilivis2022achieve,
title = {Can we achieve robustness from data alone?},
author = {Nikolaos Tsilivis and Jingtong Su and Julia Kempe},
journal = {ICML 2022 Workshop},
year = {2022}
}Nearby in Kernel and closed-form inner solvers
MMDD — Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
Deyu Bo, Xinchao Wang · ICML 2026notableVision–languagepaper ↗code ↗
Provable KRR DD — Provable and Efficient Dataset Distillation for Kernel Ridge Regression
Yilan Chen, Wei Huang, Tsui-Wei Weng · NeurIPS 2024notablepaper ↗
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Ming-Yu Chung, Sheng-Yen Chou, Chia-Mu Yu et al. · ICLR 2024notablepaper ↗
KRR-ST — Self-Supervised Dataset Distillation for Transfer Learning
Dong Bok Lee, Seanie Lee, Joonho Ko et al. · ICLR 2024corePre-training & transferpaper ↗code ↗