Related papers: Bitstream Collisions in Neural Image Compression v…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

Image compression is a ubiquitous component of modern visual pipelines, routinely applied by social media platforms and resource-constrained systems prior to inference. Despite its prevalence, the impact of compression on adversarial…

Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a…

A plethora of attack methods have been proposed to generate adversarial examples, among which the iterative methods have been demonstrated the ability to find a strong attack. However, the computation of an adversarial perturbation for a…

Deploying convolutional neural networks (CNNs) for embedded applications presents many challenges in balancing resource-efficiency and task-related accuracy. These two aspects have been well-researched in the field of CNN compression. In…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks…

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a…

The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs). However, the performance of emerging attacks is negatively…

The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing…

Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first standard for end-to-end…

Adversarial attacks play an essential role in understanding deep neural network predictions and improving their robustness. Existing attack methods aim to deceive convolutional neural network (CNN)-based classifiers by manipulating RGB…

In recent years, many forensic detectors have been proposed to detect AI-generated images and prevent their use for malicious purposes. Convolutional neural networks (CNNs) have long been the dominant architecture in this field and have…

This paper explores the possibility of extending the capability of pre-trained neural image compressors (e.g., adapting to new data or target bitrates) without breaking backward compatibility, the ability to decode bitstreams encoded by the…

As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm. In this paper, we investigate the interplay between vulnerabilities of the image scaling…

Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learned…

Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems. However, perceptual image hashing algorithms are differentiable, and are thus vulnerable to gradient-based adversarial attacks.…

With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or…

Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread…