An Access Control Method with Secret Key for Semantic Segmentation Models

• URL: http://arxiv.org/abs/2208.13135v1
• Date: Sun, 28 Aug 2022 04:09:36 GMT
• Title: An Access Control Method with Secret Key for Semantic Segmentation Models
• Authors: Teru Nagamori, Ryota Iijima, Hitoshi Kiya
• Abstract summary: A novel method for access control with a secret key is proposed to protect models from unauthorized access. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR)
• Score: 12.27887776401573
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR). Most existing access control methods focus on image classification tasks, or they are limited to CNNs. By using a patch embedding structure that ViT has, trained models and test images can be efficiently encrypted with a secret key, and then semantic segmentation tasks are carried out in the encrypted domain. In an experiment, the method is confirmed to provide the same accuracy as that of using plain images without any encryption to authorized users with a correct key and also to provide an extremely degraded accuracy to unauthorized users.

Related papers

• Disposable-key-based image encryption for collaborative learning of Vision Transformer [5.762345156477736]
  We propose a novel method for securely training the vision transformer (ViT) with sensitive data shared from multiple clients similar to privacy-preserving federated learning. In the proposed method, training images are independently encrypted by each client where encryption keys can be prepared by each client, and ViT is trained by using these encrypted images for the first time.
  arXiv  Detail & Related papers  (2024-08-11T09:55:37Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting [133.55037976429088]
  We investigate the adversarial robustness of vision transformers equipped with BERT pretraining (e.g., BEiT, MAE) A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. We propose a simple yet effective way to boost the adversarial robustness of MAE.
  arXiv  Detail & Related papers  (2023-08-20T16:27:17Z)
• Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision [49.905448429974804]
  We consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. We propose a transformer-based model for OVS, termed as OVSegmentor, which exploits web-crawled image-text pairs for pre-training. Our model achieves superior segmentation results over the state-of-the-art method by using only 3% data (4M vs 134M) for pre-training.
  arXiv  Detail & Related papers  (2023-01-22T13:10:05Z)
• Location-Aware Self-Supervised Transformers [74.76585889813207]
  We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-12-05T16:24:29Z)
• Access Control with Encrypted Feature Maps for Object Detection Models [10.925242558525683]
  In this paper, we propose an access control method with a secret key for object detection models. selected feature maps are encrypted with a secret key for training and testing models. In an experiment, the protected models allowed authorized users to obtain almost the same performance as that of non-protected models.
  arXiv  Detail & Related papers  (2022-09-29T14:46:04Z)
• Access Control of Semantic Segmentation Models Using Encrypted Feature Maps [12.29209267739635]
  We propose an access control method with a secret key for semantic segmentation models. selected feature maps are encrypted with a secret key for training and testing models. In an experiment, the protected models allowed authorized users to obtain almost the same performance as that of non-protected models.
  arXiv  Detail & Related papers  (2022-06-11T05:02:01Z)
• Simple Open-Vocabulary Object Detection with Vision Transformers [51.57562920090721]
  We propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection.
  arXiv  Detail & Related papers  (2022-05-12T17:20:36Z)
• Protection of SVM Model with Secret Key from Unauthorized Access [13.106063755117399]
  We propose a block-wise image transformation method with a secret key for support vector machine (SVM) models. Models trained by using transformed images offer a poor performance to unauthorized users without a key, while they can offer a high performance to authorized users with a key.
  arXiv  Detail & Related papers  (2021-11-17T06:41:51Z)
• Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models [13.106063755117399]
  We propose an access control method that uses the spatially invariant permutation of feature maps with a secret key for protecting semantic segmentation models. The proposed method allows rightful users with the correct key not only to access a model to full capacity but also to degrade the performance for unauthorized users.
  arXiv  Detail & Related papers  (2021-09-03T06:23:42Z)
• End-to-End Object Detection with Transformers [88.06357745922716]
  We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
  arXiv  Detail & Related papers  (2020-05-26T17:06:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.