Related papers: Security Evaluation of Compressible and Learnable …

This paper introduces a novel compatibility attack to detect a steganographic message embedded in the DCT domain of a JPEG image at high-quality factors (close to 100). Because the JPEG compression is not a surjective function, i.e. not…

Fully homomorphic encryption has allowed devices to outsource computation to third parties while preserving the secrecy of the data being computed on. Many images contain sensitive information and are commonly sent to cloud services to…

Training neural networks usually require large numbers of sensitive training data, and how to protect the privacy of training data has thus become a critical topic in deep learning research. InstaHide is a state-of-the-art scheme to protect…

Federated Learning enables one to jointly train a machine learning model across distributed clients holding sensitive datasets. In real-world settings, this approach is hindered by expensive communication and privacy concerns. Both of these…

This paper presents a novel and robust chaos-based cryptosystem for secure transmitted images and four other versions. In the proposed block encryption/decryption algorithm, a 2D chaotic map is used to shuffle the image pixel positions.…

According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns to perform tasks…

In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity.…

JPEG is one of the most popular image compression methods. It is beneficial to compress those existing JPEG files without introducing additional distortion. In this paper, we propose a deep learning based method to further compress JPEG…

Federated Learning lends itself as a promising paradigm in enabling distributed learning for autonomous vehicles applications and ensuring data privacy while enhancing and refining predictive model performance through collaborative training…

Federated learning (FL) has attracted growing attention since it allows for privacy-preserving collaborative training on decentralized clients without explicitly uploading sensitive data to the central server. However, recent works have…

Recently, a chaos-based image encryption algorithm called MCKBA (Modified Chaotic-Key Based Algorithm) was proposed. This paper analyzes the security of MCKBA and finds that it can be broken with a differential attack, which requires only…

The rapid growth of data from satellite-based Earth observation (EO) systems poses significant challenges in data transmission and storage. We evaluate the potential of task-specific learned compression algorithms in this context to reduce…

This paper presents a reversible data hiding in encrypted image that employs based notions of the RDH in plain-image schemes including histogram modification and prediction-error computation. In the proposed method, original image may be…

Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations. The current most effective defense methods against these adversarial attacks are variants of adversarial training. In this paper, we introduce a…

Image compression is a method to remove spatial redundancy between adjacent pixels and reconstruct a high-quality image. In the past few years, deep learning has gained huge attention from the research community and produced promising image…

To secure the digital images over insecure transmission channels, a new image encryption algorithm Noise-Crypt is proposed in this paper. Noise-Crypt integrates non-linear random noise, hybrid chaotic maps, and SHA-256 hashing algorithm.…

A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them…

Arithmetic Coding is an efficient lossless compression scheme applied for many multimedia standards such as JPEG, JPEG2000, H.263, H.264 and H.265. Due to nonlinearity, high error propagation and high error sensitivity of arithmetic coders,…

In federated learning for medical image analysis, the safety of the learning protocol is paramount. Such settings can often be compromised by adversaries that target either the private data used by the federation or the integrity of the…

Image compression has been the subject of extensive research for several decades, resulting in the development of well-known standards such as JPEG, JPEG2000, and H.264/AVC. However, recent advancements in deep learning have led to the…