Related papers: Human-imperceptible, Machine-recognizable Images

With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by…

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…

Federated learning is a learning method for training models over multiple participants without directly sharing their raw data, and it has been expected to be a privacy protection method for training data. In contrast, attack methods have…

With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…

Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate…

Sharing images online poses security threats to a wide range of users due to the unawareness of privacy information. Deep features have been demonstrated to be a powerful representation for images. However, deep features usually suffer from…

With the rapid advancement of artificial intelligence and deep learning, medical image analysis has become a critical tool in modern healthcare, significantly improving diagnostic accuracy and efficiency. However, AI-based methods also…

In this work, we present a novel matrix-encoding method that is particularly convenient for neural networks to make predictions in a privacy-preserving manner using homomorphic encryption. Based on this encoding method, we implement a…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide…

Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by discriminative multi-layer perceptrons and convolutional…

Protection of faces in pictures and videos of people in connection with sensitive information, activism, abused cases and others on public broadcasting media and social net- works is very important. On social networks like YouTube,facebook,…

In this paper, we propose an access control method with a secret key for object detection models for the first time so that unauthorized users without a secret key cannot benefit from the performance of trained models. The method enables us…

This work proposes a high-capacity scheme for separable reversible data hiding in encrypted images. At the sender side, the original uncompressed image is encrypted using an encryption key. One or several data hiders use the MSB of some…

This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…

Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing…

Machine learning and many of its applications are considered hard to approach due to their complexity and lack of transparency. One mission of human-centric machine learning is to improve algorithm transparency and user satisfaction while…

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework for privacy-preserving training, as it provides formal…

Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching…

Privacy-preserving neural networks have attracted increasing attention in recent years, and various algorithms have been developed to keep the balance between accuracy, computational complexity and information security from the…