# Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers Source: [Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers]() Collection index: [llms.txt]() Data updated: 2026-01-31T05:00:14.704Z Authors: Jinlin Liu, Wei Chen, Xiaojin Zhang Published: 2026-01-27T17:26:41.000Z ## Abstract Collecting web data to train deep models has become increasingly common, raising concerns about unauthorized data usage. To mitigate this issue, unlearnable examples introduce imperceptible perturbations into data, preventing models from learning effectively. However, existing methods typically rely on deep neural networks as surrogate models for perturbation generation, resulting in significant computational costs. In this work, we propose Perturbation-Induced Linearization (PIL), a computationally efficient yet effective method that generates perturbations using only linear surrogate models. PIL achieves comparable or better performance than existing surrogate-based methods while reducing computational time dramatically. We further reveal a key mechanism underlying unlearnable examples: inducing linearization to deep models, which explains why PIL can achieve competitive results in a very short time. Beyond this, we provide an analysis about the property of unlearnable examples under percentage-based partial perturbation. Our work not only provides a practical approach for data protection but also offers insights into what makes unlearnable examples effective. ## 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. - [Image Classification on CIFAR-10 (test) (Transformation Robustness)](): Image Classification; CIFAR-10 (test); Accuracy (Base): 14.7. - [Image Classification on CIFAR-10 (test)](): Image Classification; CIFAR-10 (test); Accuracy: 19.3. ## Original sources and implementation [Original paper]() [PDF]()