# Transfer Learning-Based Model Protection With Secret Key

Source: [Transfer Learning-Based Model Protection With Secret Key](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f81>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:59:51.007Z

Authors: MaungMaung AprilPyone, Hitoshi Kiya

Published: 2021-03-05T08:12:11.000Z

## Abstract

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train a large protected model like a model trained with ImageNet by using a small subset of a training dataset. It utilizes a learnable encryption step with a secret key to generate learnable transformed images. Models with pre-trained weights are fine-tuned by using such transformed images. In experiments with the ImageNet dataset, it is shown that the performance of a protected model was close to that of a non-protected model when the correct key was given, while the accuracy tremendously dropped when an incorrect key was used. The protected model was also demonstrated to be robust against key estimation attacks.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.03525>)

[PDF](<https://arxiv.org/pdf/2103.03525.pdf>)