The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks

Goethals, Sofie; Sörensen, Kenneth; Martens, David

doi:10.1145/3608482

Cited by 6 publications

(1 citation statement)

References 51 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several attempts have been made at combining explanations and privacy preservation (Franco et al, 2021 ; Rahman et al, 2021 ; Bárcena et al, 2022 ; Ariffin et al, 2023 ). Some works investigated the impact of XAI on privacy and found that the privacy of models can indeed be compromised, depending on the XAI method used (Zhao et al, 2021 ; Goethals et al, 2023 ; Lucieri et al, 2023 ; Spartalis et al, 2023 ; Yan et al, 2023 ). As a result, methods defending the privacy of explainable models have been proposed (Montenegro et al, 2021 ; Nguyen et al, 2023 ; Pentyala et al, 2023 ).…”

Section: Related Workmentioning

confidence: 99%

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

Saifullah,

Mercier,

Lucieri

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.

show abstract

Section: Related Workmentioning

confidence: 99%

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

Saifullah,

Mercier,

Lucieri

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

MCCE: Monte Carlo sampling of valid and realistic counterfactual explanations for tabular data

Redelmeier,

Jullum,

Aas

et al. 2024

Data Min Knowl Disc

View full text Add to dashboard Cite

Privacy-preserving explainable AI: a survey

Nguyen,

Huynh,

Ren

et al. 2024

Sci. China Inf. Sci.

View full text Add to dashboard Cite

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

show abstract

The Privacy Issue of Counterfactual Explanations: Explanation Linkage Attacks

Cited by 6 publications

References 51 publications

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

MCCE: Monte Carlo sampling of valid and realistic counterfactual explanations for tabular data

Privacy-preserving explainable AI: a survey

Contact Info

Product

Resources

About