Pith. sign in

REVIEW 1 cited by

Improved Adversarial Training via Learned Optimizer

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 2004.12227 v1 pith:QUMEKSZQ submitted 2020-04-25 cs.LG cs.CRstat.ML

classification cs.LGcs.CRstat.ML
keywords adversarialoptimizertraininginnermodelattackframeworkimproved
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Adversarial attack has recently become a tremendous threat to deep learning models. To improve the robustness of machine learning models, adversarial training, formulated as a minimax optimization problem, has been recognized as one of the most effective defense mechanisms. However, the non-convex and non-concave property poses a great challenge to the minimax training. In this paper, we empirically demonstrate that the commonly used PGD attack may not be optimal for inner maximization, and improved inner optimizer can lead to a more robust model. Then we leverage a learning-to-learn (L2L) framework to train an optimizer with recurrent neural networks, providing update directions and steps adaptively for the inner problem. By co-training optimizer's parameters and model's weights, the proposed framework consistently improves the model robustness over PGD-based adversarial training and TRADES.

Discussion (0). Sign in 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. Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses

    quant-ph 2025-06 conditional novelty 1.0 of 10

    A survey that categorizes known adversarial threats to quantum machine learning systems and reviews existing defenses, from logic locking to hardware-aware watermarking.

Pith tools