Pith. sign in

REVIEW 4 cited by

Adversarial Robustness as a Prior for Learned Representations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1906.00945 v2 pith:AEBDDFSR submitted 2019-06-03 stat.ML cs.CVcs.LGcs.NE

Logan Engstrom , Andrew Ilyas , Shibani Santurkar , Dimitris Tsipras , Brandon Tran , Aleksander Madry This is my paper · ORCID
classification stat.MLcs.CVcs.LGcs.NE
keywords representationslearnedadversarialdeepfeaturesgoalhigh-levelinput
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing this goal. In this work, we show that robust optimization can be re-cast as a tool for enforcing priors on the features learned by deep neural networks. It turns out that representations learned by robust models address the aforementioned shortcomings and make significant progress towards learning a high-level encoding of inputs. In particular, these representations are approximately invertible, while allowing for direct visualization and manipulation of salient input features. More broadly, our results indicate adversarial robustness as a promising avenue for improving learned representations. Our code and models for reproducing these results is available at https://git.io/robust-reps .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Accuracy Does Not Guarantee Human-Likeness: Cross-Domain Human-Centered Benchmark in Monocular Depth Estimation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Across 69 monocular depth estimators, human-likeness of error patterns peaks near human-level accuracy and declines for the most accurate models: accuracy does not guarantee human-like depth perception.

  2. Adversarial Examples Are Not Bugs, They Are Superposition

    cs.LG 2025-08 unverdicted novelty 6.0 of 10

    The paper argues that adversarial examples arise from superposition, and shows that changing superposition changes robustness and vice versa in toy models and ResNet18.

  3. Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers

    cs.CV 2026-07 conditional novelty 5.0 of 10

    FDT adds foveation and binary fixation modules to DeiT so multi-scale tokens are selected dynamically in one pass, improving ImageNet100 accuracy, MACs, and robustness without adversarial training.

  4. Sparks of Explainability: Recent Advancements in Explaining Large Vision Models

    cs.CV 2025-02 conditional novelty 2.0 of 10

    A compilation of prior peer-reviewed methods arguing that explaining vision models needs concept extraction and human alignment, not just saliency maps.

Pith tools