Related papers: Block-wise Image Transformation with Secret Key fo…

An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show…

Deepfake represents a category of face-swapping attacks that leverage machine learning models such as autoencoders or generative adversarial networks. Although the concept of the face-swapping is not new, its recent technical advances make…

Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are…

We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of…

Several companies often safeguard their trained deep models (i.e., details of architecture, learnt weights, training details etc.) from third-party users by exposing them only as black boxes through APIs. Moreover, they may not even provide…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

In this paper, we propose a privacy-preserving image classification method using encrypted images under the use of the ConvMixer structure. Block-wise scrambled images, which are robust enough against various attacks, have been used for…

This paper examines the vulnerabilities of convolutional neural networks (CNNs) to adversarial attacks and explores a method for their safeguarding. In this study, CNNs were implemented on four of the most common image datasets, namely…

Deep learning-based image watermarking, while robust against conventional distortions, remains vulnerable to advanced adversarial and regeneration attacks. Conventional countermeasures, which jointly optimize the encoder and decoder via a…

In this paper, we propose a block-wise image transformation method with a secret key for support vector machine (SVM) models. Models trained by using transformed images offer a poor performance to unauthorized users without a key, while…

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Several learnable image encryption schemes have been developed for privacy-preserving image classification. This paper focuses on the security block-based image encryption methods that are learnable and JPEG-friendly. Permuting divided…

Many recent works demonstrated that Deep Learning models are vulnerable to adversarial examples.Fortunately, generating adversarial examples usually requires white-box access to the victim model, and the attacker can only access the APIs…

Information security is one of the most challenging problems in today's technological world. In order to secure the transmission of secret data over the public network (Internet), various schemes have been presented over the last decade.…

Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent…

Previous work has suggested that preprocessing images through lossy compression can defend against adversarial perturbations, but comprehensive attack evaluations have been lacking. In this paper, we construct strong white-box and adaptive…

Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, reconstruction-based methods have emerged as a prominent…