paper-with-me

홈 › Papers

Training DNN Model with Secret Key for Model Protection

2020-08-06 · MaungMaung AprilPyone, Hitoshi Kiya

In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed images. Experiment results show that the performance of the protected model is close to that of non-protected models when the key is correct, while the accuracy is severely dropped when an incorrect key is given, and the proposed model protection is robust against not only brute-force attacks but also fine-tuning attacks, while maintaining almost the same performance accuracy as that of using a non-protected model.

📄 PDF Abstract BibTeX arXiv:2008.02450

Code (0)

등록된 구현이 없습니다.

Tasks

model

Similar Papers 제목 키워드 기반

Distributed Secret Securing in Discrete-Event Systems

2024-02-14 · Shoma Matsui, Kai Cai, Karen Rudie

In this paper, we study a security problem of protecting secrets in distributed systems. Specifically, we employ discrete-event systems to describe the structure and behaviour of distributed systems, in which global secr…

A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access

2021-09-01 · MaungMaung AprilPyone, Hitoshi Kiya

In this paper, we propose a model protection method for convolutional neural networks (CNNs) with a secret key so that authorized users get a high classification accuracy, and unauthorized users get a low classification …

Classification

Usability Aware Secret Protection with Minimum Cost

2021-02-16 · Shoma Matsui, Kai Cai

In this paper we study a cybersecurity problem of protecting system's secrets with multiple protections and a required security level, while minimizing the associated cost due to implementation/maintenance of these prote…

Secret-Protected Evolution for Differentially Private Synthetic Text Generation

2025-10-13 · Tianze Wang, Zhaoyu Chen, Jian Du, Yingtai Xiao 외 arxiv

Text data has become extremely valuable on large language models (LLMs) and even lead to general artificial intelligence (AGI). A lot of high-quality text in the real world is private and cannot be freely used due to pri…

Text Generation

A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access

2021-05-31 · AprilPyone MaungMaung, Hitoshi Kiya

In this paper, we propose a novel method for protecting convolutional neural network (CNN) models with a secret key set so that unauthorized users without the correct key set cannot access trained models. The method enab…