Pith. sign in

REVIEW 1 cited by

Can we achieve robustness from data alone?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.11727 v2 pith:WEESY2F5 submitted 2022-07-24 cs.LG cs.CV

classification cs.LGcs.CV
keywords robustdatadatasetoptimizationstandardalgorithmclassificationdescent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Discrepancy-Based Perspective on Dataset Condensation

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Dataset condensation is reframed as minimizing distribution discrepancies, and existing methods are sorted into a taxonomy; no new algorithm or experiments are provided.

Pith tools