In this paper, we introduce Selective-distillation for Class and Architecture-agnostic unleaRning (SCAR), a novel approximate unlearning method. SCAR efficiently eliminates specific information while preserving the model's test accuracy without using a retain set, which is a key component in state-of-the-art approximate unlearning algorithms. Our approach utilizes a modified Mahalanobis distance to guide the unlearning of the feature vectors of the instances to be forgotten, aligning them to the nearest wrong class distribution. Moreover, we propose a distillation-trick mechanism that distills the knowledge of the original model into the unlearning model with out-of-distribution images for retaining the original model's test performance without using any retain set. Importantly, we propose a self-forget version of SCAR that unlearns without having access to the forget set. We experimentally verified the effectiveness of our method, on three public datasets, comparing it with state-of-the-art methods. Our method obtains performance higher than methods that operate without the retain set and comparable w.r.t the best methods that rely on the retain set.

翻译：本文提出了一种新颖的近似遗忘方法——选择性蒸馏的类别与架构无关遗忘（SCAR）。SCAR能高效消除特定信息，同时无需使用当前最优近似遗忘算法中的关键组件“保留集”即可保持模型的测试精度。该方法利用修正的马氏距离指导待遗忘实例的特征向量向最近错误类分布对齐，从而实现遗忘。此外，我们提出了一种蒸馏技巧机制，通过使用分布外图像将原始模型的知识蒸馏到遗忘模型中，无需保留集即可保留原始模型的测试性能。重要的是，我们提出了SCAR的自遗忘版本，该版本无需访问遗忘集即可完成遗忘。我们在三个公开数据集上通过实验验证了该方法的有效性，并与当前最优方法进行了比较。我们的方法在无需保留集的情况下获得了优于同类方法的性能，且与依赖保留集的最优方法性能相当。