Towards an Interpretable Autoencoder: A Decision-Tree-Based Autoencoder and its Application in Anomaly Detection
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
The importance of understanding and explaining the associated classification results in the utilization of artificial intelligence (AI) in many different practical applications (e.g., cyber security and forensics) has contributed to the trend of moving away from black-box / opaque AI towards explainable AI (XAI). In this article, we propose the first interpretable autoencoder based on decision trees, which is designed to handle categorical data without the need to transform the data representation. Furthermore, our proposed interpretable autoencoder provides a natural explanation for experts in the application area. The experimental findings show that our proposed interpretable autoencoder is among the top-ranked anomaly detection algorithms, along with one-class Support Vector Machine (SVM) and Gaussian Mixture. More specifically, our proposal is on average 2% below the best Area Under the Curve (AUC) result and 3% over the other Average Precision scores, in comparison to One-class SVM, Isolation Forest, Local Outlier Factor, Elliptic Envelope, Gaussian Mixture Model, and eForest.
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 6×
“Thus, there has been recent interest in achieving model transparency and accountability in the artificial intelligence (AI; broadly defined to also include machine and deep learning techniques) literature [12].”
BackgroundInfluential“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · cited 6×
“The algorithms are sorted from left to right in ascending order of the median: eForest [25], LOF (Local Outlier Factor) [29], EE (Elliptic Envelope) [30], IF (Isolation Forest) [28], proposed DTAE, ocSVM (Oneclass SVM) [27], and GM (Gaussian Mixture).”
BackgroundMethodInfluentialThe relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · cited 6×
“The algorithms are sorted from left to right in ascending order of the median: eForest [25], LOF (Local Outlier Factor) [29], EE (Elliptic Envelope) [30], IF (Isolation Forest) [28], proposed DTAE, ocSVM (Oneclass SVM) [27], and GM (Gaussian Mixture).”
BackgroundMethodInfluentialShin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759 · cited 1×
“In other words, data to be studied is divided by layers [36], single units [37], or representation vectors.”
BackgroundObject Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545 · cited 1×
“DEEP Neural Networks (DNNs) have been utilized in detection and classification tasks for a large variety of applications, such as facial recognition [1], [2], palmprint recognition [3], visual classification [4], [5], traffic safety [6], object detection [7], [8], video captioning [9], speech recognition [10], and fau…”
MethodLOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335388 · Cited by 5,207
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · cited 7×
“of the algorithm accuracy and impartiality [15], such algorithms can potentially be utilized in high-stake/sensitive applications, such as anomaly detection [18], [19].”
BackgroundInfluentialUsing AUC and accuracy in evaluating learning algorithms
Huang, J., & Ling, C. X. (2005) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2005.50 · Cited by 2,148 · cited 4×
“TABLE 7 Statistical Results, According to AUC [53], for All the Tested Classifiers, Considering All the Tested Databases”
MethodInfluentialReview of Deep Learning Algorithms and Architectures
Shrestha, A., & Mahmood, A. (2019) · IEEE Access · doi:10.1109/access.2019.2912200 · Cited by 1,883 · cited 1×
“Autoencoders are generally built as neural networks, where these deep architectures consist of encoding and decoding blocks of non-linear layers [23].”
BackgroundInterpretable Convolutional Neural Networks
Zhang, Q., Wu, Y. N., & Zhu, S.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00920 · Cited by 833
Loyola-Gonzalez, O. (2019) · IEEE Access · doi:10.1109/access.2019.2949286 · Cited by 559
Li, O., Liu, H., Chen, C., & Rudin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11771 · Cited by 541
Entity Embeddings of Categorical Variables
Guo, C., & Berkhahn, F. (2016) · arXiv · doi:10.48550/arxiv.1604.06737 · Cited by 308 · cited 1×
“However, such an approach has two key limitations [46].”
Background
Cited by
Explainable artificial intelligence for cybersecurity: a literature survey
Charmet, F., Tanuwidjaja, H. C., Ayoubi, S., Gimenez, P.-F., Han, Y., Jmila, H., Blanc, G., Takahashi, T., & Zhang, Z. (2022) · Annals of Telecommunications · doi:10.1007/s12243-022-00926-7 · Cited by 167
A survey on explainable artificial intelligence for cybersecurity
Rjoub, G., Bentahar, J., Abdel Wahab, O., Mizouni, R., Song, A., Cohen, R., Otrok, H., & Mourad, A. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3282740 · Cited by 158
A Survey on Explainable Anomaly Detection
Li, Z., Zhu, Y., & Van Leeuwen, M. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3609333 · Cited by 139
“[4] propose the Decision Tree-based AutoEncoder (DTAE) model to detect anomalies.”
Background
Metadata
- Authors
- Aguilar, D. L., Medina-Pérez, M. A., Loyola-González, O., Choo, K.-K. R., & Bucheli-Susarrey, E.
- Venue
- IEEE Transactions on Dependable and Secure Computing
- Published
- 2023-03-01
- Volume
- 20
- Issue
- 2
- Pages
- 1048-1059
- ISSN
- 1545-5971 (ISSN-L)
- 1941-0018
- 2160-9209
- OpenAlex
- W4210712437
- Cited by
- 60
- References
- 16
- FWCI
- 4.52
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.