WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915335721975808 |
|---|---|
| author | Mesana, Patrick Bénesse, Clément Lautraite, Hadrien Caporossi, Gilles Gambs, Sébastien |
| author_facet | Mesana, Patrick Bénesse, Clément Lautraite, Hadrien Caporossi, Gilles Gambs, Sébastien |
| contents | In this paper, we introduce WaKA (Wasserstein K-nearest-neighbors Attribution), a novel attribution method that leverages principles from the LiRA (Likelihood Ratio Attack) framework and k-nearest neighbors classifiers (k-NN). WaKA efficiently measures the contribution of individual data points to the model's loss distribution, analyzing every possible k-NN that can be constructed using the training set, without requiring to sample subsets of the training set. WaKA is versatile and can be used a posteriori as a membership inference attack (MIA) to assess privacy risks or a priori for privacy influence measurement and data valuation. Thus, WaKA can be seen as bridging the gap between data attribution and membership inference attack (MIA) by providing a unified framework to distinguish between a data point's value and its privacy risk. For instance, we have shown that self-attribution values are more strongly correlated with the attack success rate than the contribution of a point to the model generalization. WaKA's different usage were also evaluated across diverse real-world datasets, demonstrating performance very close to LiRA when used as an MIA on k-NN classifiers, but with greater computational efficiency. Additionally, WaKA shows greater robustness than Shapley Values for data minimization tasks (removal or addition) on imbalanced datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01357 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles Mesana, Patrick Bénesse, Clément Lautraite, Hadrien Caporossi, Gilles Gambs, Sébastien Machine Learning Cryptography and Security In this paper, we introduce WaKA (Wasserstein K-nearest-neighbors Attribution), a novel attribution method that leverages principles from the LiRA (Likelihood Ratio Attack) framework and k-nearest neighbors classifiers (k-NN). WaKA efficiently measures the contribution of individual data points to the model's loss distribution, analyzing every possible k-NN that can be constructed using the training set, without requiring to sample subsets of the training set. WaKA is versatile and can be used a posteriori as a membership inference attack (MIA) to assess privacy risks or a priori for privacy influence measurement and data valuation. Thus, WaKA can be seen as bridging the gap between data attribution and membership inference attack (MIA) by providing a unified framework to distinguish between a data point's value and its privacy risk. For instance, we have shown that self-attribution values are more strongly correlated with the attack success rate than the contribution of a point to the model generalization. WaKA's different usage were also evaluated across diverse real-world datasets, demonstrating performance very close to LiRA when used as an MIA on k-NN classifiers, but with greater computational efficiency. Additionally, WaKA shows greater robustness than Shapley Values for data minimization tasks (removal or addition) on imbalanced datasets. |
| title | WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2411.01357 |