Related papers: Security Evaluation of Block-based Image Encryptio…

This letter discusses the problem of testing the degree of randomness within an image, particularly for a shuffled or encrypted image. Its key contributions are: 1) a mathematical model of perfectly shuffled images; 2) the derivation of the…

Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real-world problems, such as active visual exploration, where…

Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the…

Recently, an image encryption scheme based on chaotic standard and logistic maps was proposed. This paper studies the security of the scheme and shows that it can be broken with only one chosen-plaintext. Some other security defects of the…

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,…

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…

The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical…

The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks. To solve this problem, we introduce a generative deep…

Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optimal results. Recent works propose to improve the performance…

Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of…

Fairly recently, a novel image encryption based on Arnold scrambling and Lucas series has been proposed in the literature. The scheme design is based on permutation-substitution operations, where Arnold map is used to permute pixels for…

As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible modifications to an image that fool DNN classifiers. We…

With the development of imaging methods in wireless communications, enhancing the security and efficiency of image transfer requires image compression and encryption schemes. In conventional methods, encryption and compression are two…

Conventional covert image communication is assumed to transmit the message, in the securest way possible for a given payload, over lossless channels, and the associated steganographic schemes are generally vulnerable to active attacks,…

Vision is one of the essential sources through which humans acquire information. In this paper, we establish a novel framework for measuring image information content to evaluate the variation in information content during image…

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword…

Due to the widespread of advanced digital imaging devices, forgery of digital images became more serious attack patterns. In this attack scenario, the attacker tries to manipulate the digital image to conceal some meaningful information of…

This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Specifically, we study applying image transformations such as…

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against…

To protect image contents, most existing encryption algorithms are designed to transform an original image into a texture-like or noise-like image, which is, however, an obvious visual sign indicating the presence of an encrypted image,…