Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review
Authors: Sonal Allana, Mohan Kankanhalli, Rozita Dara
TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this article, we conduct a scoping review of existing literature to elicit details on the conflict between privacy and explainability. Using the standard methodology for scoping review, we extracted 57 articles from 1,943 studies published from January 2019 to December 2024. |
| Researcher Affiliation | Academia | Sonal Allana EMAIL School of Computer Science University of Guelph Mohan Kankanhalli EMAIL School of Computing National University of Singapore Rozita Dara EMAIL School of Computer Science University of Guelph |
| Pseudocode | No | The paper is a scoping review of existing literature. It describes various methods and concepts but does not include any structured pseudocode or algorithm blocks for a specific new methodology. |
| Open Source Code | No | The paper is a scoping review of existing literature and does not present a new methodology that would typically require associated source code. It references an Open Review link for the review process itself, not for source code of a described method. |
| Open Datasets | No | In this article, we conduct a scoping review of existing literature to elicit details on the conflict between privacy and explainability. Using the standard methodology for scoping review, we extracted 57 articles from 1,943 studies published from January 2019 to December 2024. The search results comprising of 3,766 studies were exported from Engineering Village and imported into Covidence (Covidence) review management software by one researcher. |
| Dataset Splits | No | This paper is a scoping review and does not conduct experiments on a specific dataset, therefore, it does not provide dataset splits. |
| Hardware Specification | No | This paper conducts a scoping review and theoretical analysis of existing literature, and therefore does not detail hardware specifications for experimental execution. |
| Software Dependencies | No | The search results comprising of 3,766 studies were exported from Engineering Village and imported into Covidence (Covidence) review management software by one researcher. This is a tool for the review process itself, not for reproducing computational experiments, and no version is given. |
| Experiment Setup | No | This paper is a scoping review of existing literature and does not involve experimental setup or hyperparameters. |