ArticleNature communications2019
Humans can decipher adversarial images.
Article in Nature communications, 2019. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 21 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
21 citing papers in PubMed.
- Model interpretability enhances domain generalization in the case of textual complexity modeling.Patterns (New York, N.Y.) · 2025Article
- Extreme image transformations affect humans and machines differently.Biological cybernetics · 2023Article
- The neuroconnectionist research programme.Nature reviews. Neuroscience · 2023Review
- Studying Healthy Psychosislike Experiences to Improve Illness Prediction.JAMA psychiatry · 2023Article
- When will AI misclassify? Intuiting failures on natural images.Journal of vision · 2023Article
- A tale of two lexica: Investigating computational pressures on word representation with neural networks.Frontiers in artificial intelligence · 2023Article
- An EANM position paper on the application of artificial intelligence in nuclear medicine.European journal of nuclear medicine and molecular imaging · 2022Article
- Brain-inspired Predictive Coding Improves the Performance of Machine Challenging Tasks.Frontiers in computational neuroscience · 2022Article
- ImageNet-trained deep neural networks exhibit illusion-like response to the Scintillating grid.Journal of vision · 2021Article
- Training for object recognition with increasing spatial frequency: A comparison of deep learning with human vision.Journal of vision · 2021Article
- Artificial cognition: How experimental psychology can help generate explainable artificial intelligence.Psychonomic bulletin & review · 2021Review
- Qualitative similarities and differences in visual object representations between brains and deep networks.Nature communications · 2021Article
- Five points to check when comparing visual perception in humans and machines.Journal of vision · 2021Article
- If deep learning is the answer, what is the question?Nature reviews. Neuroscience · 2021Review
- Adversarial radiomics: the rising of potential risks in medical imaging from adversarial learning.European journal of nuclear medicine and molecular imaging · 2020Article
- Controversial stimuli: Pitting neural networks against each other as models of human cognition.Proceedings of the National Academy of Sciences of the United States of America · 2020Observational
- Performance vs. competence in human-machine comparisons.Proceedings of the National Academy of Sciences of the United States of America · 2020Article
- Article
- Local features and global shape information in object classification by deep convolutional neural networks.Vision research · 2020Article
- Generative Feedback Explains Distinct Brain Activity Codes for Seen and Mental Images.Current biology : CB · 2020Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.