These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged.

These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged.

--As digital data transmission continues to scale, concerns about privacy grow increasingly urgent --yet privacy remains a socially constructed and ambiguously defined concept, lacking a universally accepted quantitative measure. This work examines information leakage in image data, a domain where information-theoretic guarantees are still underexplored. At the intersection of deep learning, information theory, and cryptography, we investigate the use of mutual information (MI) estimators -- in particular, the empirical estimator and the MINE framework -- to detect leakage from selectively encrypted images. Motivated by the intuition that a robust estimator would require a probabilistic frameworks that can capture spatial dependencies and residual structures -- even within encrypted representations - our work represent a promising direction for image information leakage estimation. Images are among the most common forms of data shared online, and with the widespread use of cloud storage, users frequently upload images to the web. Regardless of content sensitivity, image privacy remains a critical concern.

--We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrices are injected into each layer of the ViT architecture, and moreover, the patch embedding layer is not frozen, unlike in the case of the conventional low-rank adaptation methods. The proposed method allows us not only to reduce the number of trainable parameters but to also maintain almost the same accuracy as that of full-time tuning. The importance of vision transformer (ViT) based-models [1] has been increasing in recent years. ViT -based models can be applied to vision-language tasks [2] in addition to image classification, object detection [3], and semantic segmentation tasks [4].

A user-centric design and resource optimization should be at the center of any technology or innovation. The user-centric perspective gives the developer the opportunity to develop with task-based optimization. The user in the medical image field is a medical professional who analyzes the medical images and gives their diagnosis results to the patient. This scheme, having the medical professional user's perspective, innovates in the area of Medical Image storage and security. The architecture is designed with three main segments, namely: Segmentation, Storage, and Retrieval. This architecture was designed owing to the fact that the number of retrieval operations done by medical professionals was toweringly higher when compared to the storage operations done for some handful number of times for a particular medical image. This gives room for our innovation to segment out the medically indispensable part of the medical image, encrypt it, and store it. By encrypting the vital parts of the image using a strong encryption algorithm like the chaotic Henon map, we are able to keep the security intact. Now retrieving the medical image demands only the computationally less stressing decryption of the segmented region of interest. The decryption of the segmented region of interest results in the full recovery of the medical image which can be viewed on demand by the medical professionals for various diagnosis purposes. In this scheme, we were able to achieve a retrieval speed improvement of around 47% when compared to a full image encryption of brain medical CT images.

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box ones. In this paper, we propose a novel method using the vision transformer (ViT) that is a random ensemble of encrypted models for enhancing robustness against both white-box and black-box attacks. In addition, a benchmark attack method, called AutoAttack, is applied to models to test adversarial robustness objectively. In experiments, the method was demonstrated to be robust against not only white-box attacks but also black-box ones in an image classification task on the CIFAR-10 and ImageNet datasets. The method was also compared with the state-of-the-art in a standardized benchmark for adversarial robustness, RobustBench, and it was verified to outperform conventional defenses in terms of clean accuracy and robust accuracy.

We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually protected images but to also avoid the performance degradation caused from the use of encrypted images, whereas conventional methods cannot avoid the influence of image encryption. A domain adaptation method is used to efficiently fine-tune ViT with encrypted images. In experiments, the method is demonstrated to outperform conventional methods in an image classification task on the CIFAR-10 and ImageNet datasets in terms of classification accuracy.

In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and adversarial defenses. However, the use of transformed data decreases the performance of models. Accordingly, in this paper, we propose a novel method for fine-tuning models with transformed images under the use of the vision transformer (ViT). The proposed domain adaptation method does not cause the accuracy degradation of models, and it is carried out on the basis of the embedding structure of ViT. In experiments, we confirmed that the proposed method prevents accuracy degradation even when using encrypted images with the CIFAR-10 and CIFAR-100 datasets.

Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To reconcile this conflict, this paper proposes an efficient privacy-preserving learning paradigm, where images are first encrypted to become ``human-imperceptible, machine-recognizable'' via one of the two encryption strategies: (1) random shuffling to a set of equally-sized patches and (2) mixing-up sub-patches of the images. Then, minimal adaptations are made to vision transformer to enable it to learn on the encrypted images for vision tasks, including image classification and object detection. Extensive experiments on ImageNet and COCO show that the proposed paradigm achieves comparable accuracy with the competitive methods. Decrypting the encrypted images requires solving an NP-hard jigsaw puzzle or an ill-posed inverse problem, which is empirically shown intractable to be recovered by various attackers, including the powerful vision transformer-based attacker. We thus show that the proposed paradigm can ensure the encrypted images have become human-imperceptible while preserving machine-recognizable information. The code is available at \url{https://github.com/FushengHao/PrivacyPreservingML.}

In addition, it can maintain the same accuracy as that of models normally trained with plain images. In recent years, privacy-preserving methods for deep learning have become an urgent problem. Accordingly, we propose the 2. Related Work combined use of federated learning (FL) and encrypted images for privacy-preserving image classification under the use of 2.1 Federated Learning (FL) the vision transformer (ViT). The proposed method allows us not only to train models over multiple participants without Federated Learning (FL) [4, 5] is the scheme proposed by directly sharing their raw data but to also protect the privacy Google, in which multiple data owners can collaborate on of test (query) images for the first time.