Deep Neural Networks Are Easily Fooled

Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 427-436.

Type

Conference paper

Intellectual base

Primary research

Year

2015

DOI

10.1109/cvpr.2015.7298640

Link

https://doi.org/10.1109/CVPR.2015.7298640

Cited from

computer_science, statistics_experimental_design

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Extrapolation Beyond Sampled Regime
  • The softmax that says "panda, 99.7%" on noise is confidently wrong because the indicator tracks the regime, not the input's distance from it; catch it by asking whether the confidence was calibrated against inputs like this one.

    This sourceShows trained classifiers emit near-certain softmax confidence (≥99.6%) on noise and unrecognizable inputs, demonstrating confidence is self-blind to regime exit.

• Out Of Distribution Detection
  • A closed-set classifier always answers; OOD detection adds the option to abstain. Not a confidence threshold alone. Low softmax confidence is not OOD detection: networks are notoriously confidently wrong on novel inputs.

    This sourceDemonstrates DNNs assigning ≥99% softmax confidence to evolved, human-unrecognizable images — direct evidence that networks are confidently wrong on novel/garbage inputs.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Links previously used in the corpus

Before the registry existed this work was also linked 1 other way.

• https://openaccess.thecvf.com/content_cvpr_2015/html/Nguyen_Deep_Neural_Networks_2015_CVPR_paper.html ×1

Registry ID ref:ba17df07d885 · see in the full table