English

Deep Classifier Mimicry without Data Access

Machine Learning 2024-04-29 v5 Artificial Intelligence

Abstract

Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may not equally be granted. This makes it tremendously challenging to fine-tune, compress models, adapt continually, or to do any other type of data-driven update. We posit that original data access may however not be required. Specifically, we propose Contrastive Abductive Knowledge Extraction (CAKE), a model-agnostic knowledge distillation procedure that mimics deep classifiers without access to the original data. To this end, CAKE generates pairs of noisy synthetic samples and diffuses them contrastively toward a model's decision boundary. We empirically corroborate CAKE's effectiveness using several benchmark datasets and various architectural choices, paving the way for broad application.

Cite

@article{arxiv.2306.02090,
  title  = {Deep Classifier Mimicry without Data Access},
  author = {Steven Braun and Martin Mundt and Kristian Kersting},
  journal= {arXiv preprint arXiv:2306.02090},
  year   = {2024}
}

Comments

11 pages main, 4 figures, 2 tables, 4 pages appendix

R2 v1 2026-06-28T10:55:25.904Z