# Dataset Inference: Ownership Resolution in Machine Learning Source: [Dataset Inference: Ownership Resolution in Machine Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:08:38.583Z Authors: Pratyush Maini, Mohammad Yaghini, Nicolas Papernot Published: 2021-04-21T18:12:18.000Z ## Abstract With increasingly more data and computation involved in their training, machine learning models constitute valuable intellectual property. This has spurred interest in model stealing, which is made more practical by advances in learning with partial, little, or no supervision. Existing defenses focus on inserting unique watermarks in a model's decision surface, but this is insufficient: the watermarks are not sampled from the training distribution and thus are not always preserved during model stealing. In this paper, we make the key observation that knowledge contained in the stolen model's training set is what is common to all stolen copies. The adversary's goal, irrespective of the attack employed, is always to extract this knowledge or its by-products. This gives the original model's owner a strong advantage over the adversary: model owners have access to the original training data. We thus introduce $dataset$ $inference$, the process of identifying whether a suspected model copy has private knowledge from the original model's dataset, as a defense against model stealing. We develop an approach for dataset inference that combines statistical testing with the ability to estimate the distance of multiple data points to the decision boundary. Our experiments on CIFAR10, SVHN, CIFAR100 and ImageNet show that model owners can claim with confidence greater than 99% that their model (or dataset as a matter of fact) was stolen, despite only exposing 50 of the stolen model's training points. Dataset inference defends against state-of-the-art attacks even when the adversary is adaptive. Unlike prior work, it does not require retraining or overfitting the defended model. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Dataset Tracking on FairFace](): Dataset Tracking; FairFace; Count A 1 (out of 20): 0. - [Dataset Tracking on CIFAR-10](): Dataset Tracking; CIFAR-10; Component Score A 1: 1. ## Original sources and implementation [Original paper]() [PDF]()