Related papers: Security Evaluation of Compressible Image Encrypti…

Chaotic systems have been broadly exploited through the last two decades to build encryption methods. Recently, two new image encryption schemes have been proposed, where the encryption process involves a permutation operation and an…

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,…

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…

Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible…

We develop the proposal of non-systematic channel codes on the AWGN wire-tap channel. Such coding technique, based on scrambling, achieves high transmission security with a small degradation of the eavesdropper's channel with respect to the…

The Internet is a ubiquitous and affordable communications network suited for e-commerce and medical image communications. Security has become a major issue as data communication channels can be intruded by intruders during transmission.…

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…

This paper analyzes security performance of an image encryption algorithm using 2D lag-complex Logistic map (LCLM), which adopts it as a pseudo-random number generator, and uses the sum of all pixel values of the plain-image as its initial…

This paper proposes an improved steganography approach for hiding text messages in lossless RGB images. The objective of this work is to increase the security level and to improve the storage capacity with compression techniques. The…

We propose a novel method for privacy-preserving fine-tuning vision transformers (ViTs) with encrypted images. Conventional methods using encrypted images degrade model performance compared with that of using plain images due to the…

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Image perceptual hashing finds applications in content indexing, large-scale image database management, certification and authentication and digital watermarking. We propose a Block-DCT and PCA based image perceptual hash in this article…

There are some good combinatorial structures suitable for image encryption. In this study, a new chaotic image encryption algorithm based on transversals in a Latin square is proposed. By means of an n-transversal of a Latin square, we can…

Traditional permutation schemes mostly focus on random scrambling of pixels, often neglecting the intrinsic image information that could enhance diffusion in image encryption algorithms. This paper introduces PermutEx, a…

In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

Cloud-based machine learning services (CMLS) enable organizations to take advantage of advanced models that are pre-trained on large quantities of data. The main shortcoming of using these services, however, is the difficulty of keeping the…

We study the robustness of learned image compression models against adversarial attacks and present a training-free defense technique based on simple image transform functions. Recent learned image compression models are vulnerable to…