Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
The last decade has witnessed the proliferation of Deep Learning models in many applications, achieving unrivaled levels of predictive performance. Unfortunately, the black-box nature of Deep Learning models has posed unanswered questions about what they learn from data. Certain application scenarios have highlighted the importance of assessing the bounds under which Deep Learning models operate, a problem addressed by using assorted approaches aimed at audiences from different domains. However, as the focus of the application is placed more on non-expert users, it results mandatory to provide the means for him/her to trust the model, just like a human gets familiar with a system or process: by understanding the hypothetical circumstances under which it fails. This is indeed the angular stone for this research work: to undertake an adversarial analysis of a Deep Learning model. The proposed framework constructs counterfactual examples by ensuring their plausibility, e.g. there is a reasonable probability that a human could generate them without resorting to a computer program. Therefore, this work must be regarded as valuable auditing exercise of the usable bounds a certain model is constrained within, thereby allowing for a much greater understanding of the capabilities and pitfalls of a model used in a real application. To this end, a Generative Adversarial Network (GAN) and multi-objective heuristics are used to furnish a plausible attack to the audited model, efficiently trading between the confusion of this model, the intensity and plausibility of the generated counterfactual. Its utility is showcased within a human face classification task, unveiling the enormous potential of the proposed framework.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Self-citationDropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021 · cited 1×
“aim at generating samples of incredibly complex distributions like photo-realistic human faces [17], [18].”
BackgroundAttGAN: Facial attribute editing by only changing what you want
He, Z., Zuo, W., Kan, M., Shan, S., & Chen, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2916751 · Cited by 833 · cited 5×
“The framework proposed here hybridizes these two approaches by extending what was introduced by [19], to include the idea of performing an adversarial analysis of a third model.”
BackgroundMethodInfluentialDiez-Olivan, A., Del Ser, J., Galar, D., & Sierra, B. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.10.005 · Cited by 633 · cited 1×
“0 [3], and a myriad of mobile applications to help users with their daily lives [4]–[6].”
BackgroundCan Deep Learning Revolutionize Mobile Sensing?
Lane, N. D., & Georgiev, P. (2015) · Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications · doi:10.1145/2699343.2699349 · Cited by 282
Cited by
Holzinger, A., Malle, B., Saranti, A., & Pfeifer, B. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.01.008 · Cited by 352
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, A.-H., Barthe, G., Schölkopf, B., & Valera, I. (2023) · ACM Computing Surveys · doi:10.1145/3527848 · Cited by 301
Random forest explainability using counterfactual sets
Fernández, R. R., Martín de Diego, I., Aceña, V., Fernández-Isabel, A., & Moguerza, J. M. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.07.001 · Cited by 73
Discriminative attribution from paired images
Eckstein, N., Bukhari, H., Bates, A. S., Jefferis, G. S. X. E., & Funke, J. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-25069-9_27 · Cited by 5
Metadata
- Authors
- Barredo-Arrieta, A., & Del Ser, J.
- Venue
- 2020 International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Published
- 2020-07
- Pages
- 1-7
- OpenAlex
- W3013540672
- Cited by
- 32
- References
- 7
- FWCI
- 2.52
- Type
- conference paper
- Language
- en
- Open access
- green
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: Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples. https://app.cochat.ai/papers/10.1109/ijcnn48605.2020.9206728
- The paper
- Barredo-Arrieta, A., & Del Ser, J. (2020). Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples. 2020 International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/ijcnn48605.2020.9206728
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.