Adversarial vulnerabilities of human decision-making
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Significance: “What I cannot efficiently break, I cannot understand.” Understanding the vulnerabilities of human choice processes allows us to detect and potentially avoid adversarial attacks. We develop a general framework for creating adversaries for human decision-making. The framework is based on recent developments in deep reinforcement learning models and recurrent neural networks and can in principle be applied to any decision-making task and adversarial objective. We show the performance of the framework in three tasks involving choice, response inhibition, and social decision-making. In all of the cases the framework was successful in its adversarial attack. Furthermore, we show various ways to interpret the models to provide insights into the exploitability of human choice.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810
Addressing Function Approximation Error in Actor-Critic Methods
Fujimoto, S., van Hoof, H., & Meger, D. (2018) · arXiv · doi:10.48550/arxiv.1802.09477 · Cited by 3,650 · cited 1×
“This covariate shift phenomenon is known as “extrapolation error” in the batch reinforcement learning literature (19) and several solutions have been suggested (see also ref.”
BackgroundGetting to Know You: Reputation and Trust in a Two-Person Economic Exchange
King-Casas, B., Tomlin, D., Anen, C., Camerer, C. F., Quartz, S. R., & Montague, P. R. (2005) · Science · doi:10.1126/science.1108062 · Cited by 1,345 · cited 2×
“To show the promise of this framework to surface such vulnerabilities in human subjects, we applied it to three decision-making tasks involving choice engineering (1), response inhibition (8), and a social exchange game (9) and tested the resulting adversaries on volunteers to assess the biases.”
BackgroundMethodPositive reciprocity and intentions in trust games
McCabe, K. A., Rigdon, M. L., & Smith, V. L. (2003) · Journal of Economic Behavior & Organization · doi:10.1016/s0167-2681(03)00003-9 · Cited by 659
Learning to reinforcement learn
Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., Blundell, C., Kumaran, D., & Botvinick, M. (2016) · arXiv · doi:10.48550/arxiv.1611.05763 · Cited by 579 · cited 1×
“CO G N IT IV E SC IE N CE S There would then be a parallel with the learning to reinforcement learn (16) or RL(2) (17) frameworks.”
Background
Cited by
Human-like systematic generalization through a meta-learning neural network
Lake, B. M., & Baroni, M. (2023) · Nature · doi:10.1038/s41586-023-06668-3 · Cited by 230
Williamson, S. M., & Prybutok, V. (2024) · Information · doi:10.3390/info15060299 · Cited by 146
Human-centred mechanism design with Democratic AI
Koster, R., Balaguer, J., Tacchetti, A., Weinstein, A., Zhu, T., Hauser, O., Williams, D., Campbell-Gillingham, L., Thacker, P., Botvinick, M., et al. (2022) · Nature Human Behaviour · doi:10.1038/s41562-022-01383-x · Cited by 84
The University of North Carolina at Charlotte, Zhou, L., Rudin, C., Duke University, Gombolay, M., Georgia Institute of Technology, Spohrer, J., International Society of Service Innovation Professionals, Zhou, M., Juji, et al. (2023) · AIS Transactions on Human-Computer Interaction · doi:10.17705/1thci.00085 · Cited by 20
Metadata
- Authors
- Dezfouli, A., Nock, R., & Dayan, P.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2020-11-04
- Volume
- 117
- Issue
- 46
- Pages
- 29221-29228
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W3097193392
- Cited by
- 36
- References
- 6
- FWCI
- 1.70
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: Adversarial vulnerabilities of human decision-making. https://app.cochat.ai/papers/10.1073/pnas.2016921117
- The paper
- Dezfouli, A., Nock, R., & Dayan, P. (2020). Adversarial vulnerabilities of human decision-making. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2016921117
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.