Related papers: Block-Wise Encryption for Reliable Vision Transfor…

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

In this paper, we propose a privacy-preserving image classification method that uses encrypted images and an isotropic network such as the vision transformer. The proposed method allows us not only to apply images without visual information…

In this paper, some existing perceptual encryption algorithms of MPEG videos are reviewed and some problems, especially security defects of two recently proposed MPEG-video perceptual encryption schemes, are pointed out. Then, a simpler and…

Fully homomorphic encryption has allowed devices to outsource computation to third parties while preserving the secrecy of the data being computed on. Many images contain sensitive information and are commonly sent to cloud services to…

We propose an optical encryption framework that can encrypt and decrypt large-sized images beyond the size of the encrypted image using our two methods: random phase-free method and scaled diffraction. In order to record the entire image…

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 accuracy. The…

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…

We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption method proposed for EtC systems with JPEG compression. In this…

In this paper we present the first baseline results for the task of few-shot learning of discrete embedding vectors for image recognition. Few-shot learning is a highly researched task, commonly leveraged by recognition systems that are…

Face recognition has recently become ubiquitous in many scenes for authentication or security purposes. Meanwhile, there are increasing concerns about the privacy of face images, which are sensitive biometric data that should be carefully…

Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures represent features…

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…

In this paper, we propose a privacy-preserving image classification method using encrypted images under the use of the ConvMixer structure. Block-wise scrambled images, which are robust enough against various attacks, have been used for…

Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images. Despite their significant improvements, most existing methods still focus on the most…

In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two…

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-based methods mainly focus on the de-identification against…

Deep hamming hashing has gained growing popularity in approximate nearest neighbour search for large-scale image retrieval. Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network…

In this paper, two image encryption schemes are proposed for grayscale and color images. The two encryption schemes are based on dividing each image into blocks of different sizes. In the first scheme, the two dimension ($2$D) input image…

A privacy-preserving clothing classification scheme is presented to enable secure occupant-centric control (OCC) systems. Although the utilization of camera images for HVAC control has been widely studied to optimize thermal comfort,…

Machine learning techniques for more efficient video compression and video enhancement have been developed thanks to breakthroughs in deep learning. The new techniques, considered as an advanced form of Artificial Intelligence (AI), bring…