Related papers: Human-imperceptible, Machine-recognizable Images

Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge…

Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of…

Images vary in how memorable they are to humans. Inspired by findings from cognitive science and computer vision, we explore correlates of image memorability in pretrained transformer-based vision encoders for the first time. Focusing…

As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the…

In this paper, a privacy preserving image classification method is proposed under the use of ConvMixer models. To protect the visual information of test images, a test image is divided into blocks, and then every block is encrypted by using…

Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vision, speech recognition, object detection, to name a few. The principal reason for this success is the availability of huge datasets for…

How can multiple distributed entities collaboratively train a shared deep net on their private data while preserving privacy? This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing…

With the extensive applications of machine learning, the issue of private or sensitive data in the training examples becomes more and more serious: during the training process, personal information or habits may be disclosed to unexpected…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

In this paper, we propose a novel learnable image encryption method for privacy-preserving deep neural networks (DNNs). The proposed method is carried out on the basis of block scrambling used in combination with data augmentation…

Recently, the enactment of privacy regulations has promoted the rise of the machine unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise unlearning, such that a learnt model will not expose user's privacy…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

Privacy preserving machine learning is an active area of research usually relying on techniques such as homomorphic encryption or secure multiparty computation. Recent novel encryption techniques for performing machine learning using deep…

Visual Cryptography is a special encryption technique to hide information in images, which divide secret image into multiple layers. Each layer holds some information. The receiver aligns the layers and the secret information is revealed by…

The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains autoencoders with Neural…

The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…

Data protection methods like cryptography, despite being effective, inadvertently signal the presence of secret communication, thereby drawing undue attention. Here, we introduce an optical information hiding camera integrated with an…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

We propose an image identification scheme for double-compressed encrypted JPEG images that aims to identify encrypted JPEG images that are generated from an original JPEG image. To store images without any visual sensitive information on…