Related papers: Coverless Information Hiding Based on Generative a…
Until now hiding methods in network steganography have been described in arbitrary ways, making them difficult to compare. For instance, some publications describe classical channel characteristics, such as robustness and bandwidth, while…
Generative adversarial nets (GANs) have been widely studied during the recent development of deep learning and unsupervised learning. With an adversarial training mechanism, GAN manages to train a generative model to fit the underlying…
We propose a novel image transformation scheme using generative adversarial networks (GANs) for privacy-preserving deep neural networks (DNNs). The proposed scheme enables us not only to apply images without visual information to DNNs, but…
Mode collapse is a critical problem in training generative adversarial networks. To alleviate mode collapse, several recent studies introduce new objective functions, network architectures or alternative training schemes. However, their…
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…
There are five features to consider when using generative adversarial networks to apply makeup to photos of the human face. These features include (1) facial components, (2) interactive color adjustments, (3) makeup variations, (4)…
With the advancement of communication technology,data is exchanged digitally over the network. At the other side the technology is also proven as a tool for unauthorized access to attackers. Thus the security of data to be transmitted…
With the explosive growth of internet and the fast communication techniques in recent years the security and the confidentiality of the sensitive data has become of prime and supreme importance and concern. To protect this data from…
Steganography is the art and science of hiding secret messages in public communication so that the presence of the secret messages cannot be detected. There are two distribution-preserving steganographic frameworks, one is sampling-based…
In this paper, a novel steganographic scheme based on chaotic iterations is proposed. This research work takes place into the information hiding framework, and focus more specifically on robust steganography. Steganographic algorithms can…
Generative Adversarial Networks (GANs) have facilitated a new direction to tackle the image-to-image transformation problem. Different GANs use generator and discriminator networks with different losses in the objective function. Still…
As deepfake technologies continue to advance, passive detection methods struggle to generalize with various forgery manipulations and datasets. Proactive defense techniques have been actively studied with the primary aim of preventing…
As the multimedia and internet technologies are growing fast, the transmission of digital media plays an important role in communication. The various digital media like audio, video and images are being transferred through internet. There…
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network. Our model consists of a top-down…
Image content is a predominant factor in marketing campaigns, websites and banners. Today, marketers and designers spend considerable time and money in generating such professional quality content. We take a step towards simplifying this…
Convolutional Neural Networks (CNN) based methods have significantly improved the performance of image steganalysis compared with conventional ones based on hand-crafted features. However, many existing literatures on computer vision have…
While Generative Adversarial Networks (GANs) have recently found applications in image editing, most previous GAN-based image editing methods require largescale datasets with semantic segmentation annotations for training, only provide high…
Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains…
Adding perturbations to images can mislead classification models to produce incorrect results. Recently, researchers exploited adversarial perturbations to protect image privacy from retrieval by intelligent models. However, adding…
The need to protect sensitive information privacy duringinformation exchange over the internet/intranet has led towider adoption of cryptography and steganography. The cryptography approaches convert the information into an unreadable…