Dominik Ślęzak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dominik Ślęzak has a total of 99 co-authors. Here are the top co-authors by number of shared publications:
- Andrzej Janusz
Queensland University of Technology
9 shared publications Andrzej Janusz
University of Warsaw
5 shared publicationsSebastian Stawicki
5 shared publications- Marcin Szczuka
University of Warsaw
4 shared publications - Marek Sikora
Department of Computer Networks and Systems, Silesian University of Technology, 44-100 Gliwice, Poland
4 shared publications - Andrzej Skowron
Systems Research Institute, Polish Academy of Sciences
3 shared publications
Latest Publications
- Open Access
- 1 October 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (4) , 112
Adversarial Attacks Detection Method for Tabular Data
Adversarial attacks involve malicious actors introducing intentional perturbations to machine learning (ML) models, causing unintended behavior. This poses a significant threat to the integrity and trustworthiness of ML models, necessitating the development of robust detection techniques to protect systems from potential threats. The paper proposes a new approach for detecting adversarial attacks using a surrogate model and diagnostic attributes. The method was tested on 22 tabular datasets on which four different ML models were trained. Furthermore, various attacks were conducted, which led to obtaining perturbed data. The proposed approach is characterized by high efficiency in detecting known and unknown attacks—balanced accuracy was above 0.94, with very low false negative rates (0.02–0.10) for binary detection. Sensitivity analysis shows that classifiers trained based on diagnostic attributes can detect even very subtle adversarial attacks.
- 1 October 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (4) , 112
Open AccessAdversarial Attacks Detection Method for Tabular Data
Adversarial attacks involve malicious actors introducing intentional perturbations to machine learning (ML) models, causing unintended behavior. This poses a significant threat to the integrity and trustworthiness of ML models, necessitating the development of robust detection techniques to protect systems from potential threats. The paper proposes a new approach for detecting adversarial attacks using a surrogate model and diagnostic attributes. The method was tested on 22 tabular datasets on which four different ML models were trained. Furthermore, various attacks were conducted, which led to obtaining perturbed data. The proposed approach is characterized by high efficiency in detecting known and unknown attacks—balanced accuracy was above 0.94, with very low false negative rates (0.02–0.10) for binary detection. Sensitivity analysis shows that classifiers trained based on diagnostic attributes can detect even very subtle adversarial attacks.
- Open Access
- 10 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Rule generation in Rough set Non-deterministic Information Analysis (RNIA) and some applications of the obtained rules
- 10 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Open AccessRule generation in Rough set Non-deterministic Information Analysis (RNIA) and some applications of the obtained rules
- 25 July 2024
- Published by Springer Nature
- p. 18-33
On Tolerance-Based Rough Set Operators and Their Covering Generalizations
- 25 July 2024
- Published by Springer Nature
- p. 18-33
On Tolerance-Based Rough Set Operators and Their Covering Generalizations
- 25 July 2024
- Published by Springer Nature
- p. 120-133
Consideration of Detecting Data and Functional Dependency in Tabular Data with Missing Values by the Obtained Rules
- 25 July 2024
- Published by Springer Nature
- p. 120-133
Consideration of Detecting Data and Functional Dependency in Tabular Data with Missing Values by the Obtained Rules
- 25 July 2024
- Published by Springer Nature
- p. 34-49
Parametrized $\gamma $-Decision Valuation for Variable Precision Rough Set Model- 25 July 2024
- Published by Springer Nature
- p. 34-49
Parametrized $\gamma $-Decision Valuation for Variable Precision Rough Set Model- 31 December 2023
- Published by Springer Nature
- p. 479-494
On Several New Dempster-Shafer-Inspired Uncertainty Measures Applicable for Active Learning
- 31 December 2023
- Published by Springer Nature
- p. 479-494
On Several New Dempster-Shafer-Inspired Uncertainty Measures Applicable for Active Learning
- Open Access
- 17 November 2023
- Published by Elsevier in Journal of Forensic and Legal Medicine
- Vol. 101, 102619
Using expert-reviewed CSAM to train CNNs and its anthropological analysis
- 17 November 2023
- Published by Elsevier in Journal of Forensic and Legal Medicine
- Vol. 101, 102619
Open AccessUsing expert-reviewed CSAM to train CNNs and its anthropological analysis
- Open Access
- 28 September 2023
- Published by IOS Press
- p. 1207-1214
Robust Assignment of Labels for Active Learning with Sparse and Noisy Annotations
The performance of classification models depends on the quality of training data labels. Unfortunately, acquiring good-quality annotations for many tasks is infeasible or too expensive. To address this challenge, active learning algorithms are commonly employed to select only the most relevant data for labeling. However, this is possible only when the quality and quantity of labels acquired from experts are sufficient. In many applications, a trade-off between annotating individual samples by multiple annotators to increase label quality vs. annotating new samples to increase the total number of labeled instances is necessary. In this paper, we address the issue of faulty data annotations in the context of active learning. In particular, we propose two novel annotation unification algorithms that utilize unlabeled parts of the sample space. The proposed methods require little to no intersection between samples annotated by different experts. Our experiments on four public datasets indicate the robustness and superiority of the proposed methods in both, the estimation of the annotator's reliability, and the assignment of actual labels, against the state-of-the-art algorithms and the simple majority voting.
- 28 September 2023
- Published by IOS Press
- p. 1207-1214
Open AccessRobust Assignment of Labels for Active Learning with Sparse and Noisy Annotations
The performance of classification models depends on the quality of training data labels. Unfortunately, acquiring good-quality annotations for many tasks is infeasible or too expensive. To address this challenge, active learning algorithms are commonly employed to select only the most relevant data for labeling. However, this is possible only when the quality and quantity of labels acquired from experts are sufficient. In many applications, a trade-off between annotating individual samples by multiple annotators to increase label quality vs. annotating new samples to increase the total number of labeled instances is necessary. In this paper, we address the issue of faulty data annotations in the context of active learning. In particular, we propose two novel annotation unification algorithms that utilize unlabeled parts of the sample space. The proposed methods require little to no intersection between samples annotated by different experts. Our experiments on four public datasets indicate the robustness and superiority of the proposed methods in both, the estimation of the annotator's reliability, and the assignment of actual labels, against the state-of-the-art algorithms and the simple majority voting.
- 30 June 2023
- Published by Elsevier in Information Sciences
- Vol. 645
A practical study of methods for deriving insightful attribute importance rankings using decision bireducts
- 30 June 2023
- Published by Elsevier in Information Sciences
- Vol. 645
A practical study of methods for deriving insightful attribute importance rankings using decision bireducts
- 11 April 2023
- Published by Elsevier in Applied Soft Computing
- Vol. 141
BrightBox — A rough set based technology for diagnosing mistakes of machine learning models
- 11 April 2023
- Published by Elsevier in Applied Soft Computing
- Vol. 141
BrightBox — A rough set based technology for diagnosing mistakes of machine learning models