{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:44:42Z","timestamp":1772909082840,"version":"3.50.1"},"reference-count":0,"publisher":"Privacy Enhancing Technologies Symposium Advisory Board","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["PoPETs"],"abstract":"<jats:p>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\u2019s 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\u2019s 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\u2019s different usages 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.<\/jats:p>","DOI":"10.56553\/popets-2025-0110","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T03:14:51Z","timestamp":1747624491000},"page":"494-526","source":"Crossref","is-referenced-by-count":1,"title":["WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles"],"prefix":"10.56553","volume":"2025","author":[{"given":"Patrick","family":"Mesana","sequence":"first","affiliation":[{"name":"HEC Montr\u00e9al"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cl\u00e9ment","family":"B\u00e9nesse","sequence":"additional","affiliation":[{"name":"University du Qu\u00e9bec \u00e0 Montr\u00e9al"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadrien","family":"Lautraite","sequence":"additional","affiliation":[{"name":"University du Qu\u00e9bec \u00e0 Montr\u00e9al"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilles","family":"Caporossi","sequence":"additional","affiliation":[{"name":"HEC Montr\u00e9al"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9bastien","family":"Gambs","sequence":"additional","affiliation":[{"name":"University du Qu\u00e9bec \u00e0 Montr\u00e9al"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"35752","published-online":{"date-parts":[[2025,7]]},"container-title":["Proceedings on Privacy Enhancing Technologies"],"original-title":[],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T03:15:02Z","timestamp":1747624502000},"score":1,"resource":{"primary":{"URL":"https:\/\/petsymposium.org\/popets\/2025\/popets-2025-0110.php"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["10.56553\/popets-2025-0110"],"URL":"https:\/\/doi.org\/10.56553\/popets-2025-0110","relation":{},"ISSN":["2299-0984"],"issn-type":[{"value":"2299-0984","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}