Related papers: Access Control with Encrypted Feature Maps for Obj…

The issue of detecting deepfakes has garnered significant attention in the research community, with the goal of identifying facial manipulations for abuse prevention. Although recent studies have focused on developing generalized models…

Inference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets…

In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper…

In the realm of multimedia data analysis, the extensive use of image datasets has escalated concerns over privacy protection within such data. Current research predominantly focuses on privacy protection either in data sharing or upon the…

Object detection is a crucial task in computer vision that aims to identify and localize objects in images or videos. The recent advancements in deep learning and Convolutional Neural Networks (CNNs) have significantly improved the…

Recently, with the support of mobile cloud computing, a large number of health related data collected from various body sensor networks can be managed efficiently. However, to ensure data security and data privacy in cloud-integrated body…

Lensless imaging can provide visual privacy due to the highly multiplexed characteristic of its measurements. However, this alone is a weak form of security, as various adversarial attacks can be designed to invert the one-to-many scene…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

We present a novel privacy-preserving scheme for deep neural networks (DNNs) that enables us not to only apply images without visual information to DNNs for both training and testing but to also consider data augmentation in the encrypted…

Network intrusions have become a significant threat in recent years as a result of the increased demand of computer networks for critical systems. Intrusion detection system (IDS) has been widely deployed as a defense measure for computer…

With rapid progress of Virtual Reality and Augmented Reality technologies, 3D contents are the next widespread media in many applications. Thus, the protection of 3D models is primarily important. Encryption of 3D models is essential to…

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…

A new image encryption scheme using the advanced encryption standard (AES), a chaotic map, a genetic operator, and a fuzzy inference system is proposed in this paper. In this work, plain images were used as input, and the required security…

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure,…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…