Humans can decipher adversarial images
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Does the human mind resemble the machine-learning systems that mirror its performance? Convolutional neural networks (CNNs) have achieved human-level benchmarks in classifying novel images. These advances support technologies such as autonomous vehicles and machine diagnosis; but beyond this, they serve as candidate models for human vision itself. However, unlike humans, CNNs are “fooled” by adversarial examples—nonsense patterns that machines recognize as familiar objects, or seemingly irrelevant image perturbations that nevertheless alter the machine’s classification. Such bizarre behaviors challenge the promise of these new advances; but do human and machine judgments fundamentally diverge? Here, we show that human and machine classification of adversarial images are robustly related: In 8 experiments on 5 prominent and diverse adversarial imagesets, human subjects correctly anticipated the machine’s preferred label over relevant foils—even for images described as “totally unrecognizable to human eyes”. Human intuition may be a surprisingly reliable guide to machine (mis)classification—with consequences for minds and machines alike.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep learning for visual understanding: A review
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., & Lew, M. S. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.09.116 · Cited by 2,504
Robust physical-world attacks on deep learning visual classification
Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00175 · Cited by 2,173
Using goal-driven deep learning models to understand sensory cortex
Yamins, D. L. K., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4244 · Cited by 1,621
Evaluating amazon’s mechanical turk as a tool for experimental behavioral research
Crump, M. J. C., McDonnell, J. V., & Gureckis, T. M. (2013) · PLoS ONE · doi:10.1371/journal.pone.0057410 · Cited by 1,617
Cited by
If deep learning is the answer, what is the question?
Saxe, A., Nelli, S., & Summerfield, C. (2021) · Nature Reviews Neuroscience · doi:10.1038/s41583-020-00395-8 · Cited by 397
Deep Learning: The Good, the Bad, and the Ugly
Serre, T. (2019) · Annual Review of Vision Science · doi:10.1146/annurev-vision-091718-014951 · Cited by 267
The neuroconnectionist research programme
Doerig, A., Sommers, R. P., Seeliger, K., Richards, B., Ismael, J., Lindsay, G. W., Kording, K. P., Konkle, T., van Gerven, M. A. J., Kriegeskorte, N., et al. (2023) · Nature Reviews Neuroscience · doi:10.1038/s41583-023-00705-w · Cited by 233
Performance vs. competence in human–machine comparisons
Firestone, C. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1905334117 · Cited by 150
Self-citationThe Rhetoric and Reality of Anthropomorphism in Artificial Intelligence
Watson, D. (2019) · Minds and Machines · doi:10.1007/s11023-019-09506-6 · Cited by 148
Metadata
- Authors
- Zhou, Z., & Firestone, C.
- Venue
- Nature Communications
- Published
- 2019-03-22
- Volume
- 10
- Issue
- 1
- Pages
- 1334-1334
- ISSN
- 2041-1723 (ISSN-L)
- OpenAlex
- W2919093153
- Cited by
- 73
- References
- 14
- FWCI
- 3.68
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Humans can decipher adversarial images. https://app.cochat.ai/papers/10.1038/s41467-019-08931-6
- The paper
- Zhou, Z., & Firestone, C. (2019). Humans can decipher adversarial images. Nature Communications. https://doi.org/10.1038/s41467-019-08931-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.