Related papers: Decoupling Defense Strategies for Robust Image Wat…

Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1)…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. However, it often degrades the model performance on normal images and the defense does not generalize well to novel attacks. Given the…

Digital information revolution has brought about many advantages and new issues. The protection of ownership and the prevention of unauthorized manipulation of digital audio, image, and video materials has become an important concern due to…

The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collapse. To address this…

Recent research has demonstrated that adding some imperceptible perturbations to original images can fool deep learning models. However, the current adversarial perturbations are usually shown in the form of noises, and thus have no…

With the rapid development of deep learning, object detectors have demonstrated impressive performance; however, vulnerabilities still exist in certain scenarios. Current research exploring the vulnerabilities using adversarial patches…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

The rapid growth of Artificial Intelligence-Generated Content (AIGC) raises concerns about the authenticity of digital media. In this context, image self-recovery, reconstructing original content from its manipulated version, offers a…

To address the security risk caused by fixed offset mapping and the limited recoverability of random mapping used in image watermarking, we propose an image self-embedding fragile watermarking algorithm based on deneighborhood mapping.…

With rich visual data, such as images, becoming readily associated with items, visually-aware recommendation systems (VARS) have been widely used in different applications. Recent studies have shown that VARS are vulnerable to item-image…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Invisible watermarking is essential for tracing the provenance of digital content. However, training state-of-the-art models remains notoriously difficult, with current approaches often struggling to balance robustness against true…

Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to perturbations poses a significant threat to their reliability in real-world applications. Despite often being…

Digital watermarking is the process of embedding secret information by altering images in an undetectable way to the human eye. To increase the robustness of the model, many deep learning-based watermarking methods use the…

We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries.…

Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically align the prediction distributions of unsafe prompts with those…

In unsecured network environments, ownership protection of digital contents, such as images, is becoming a growing concern. Different watermarking methods have been proposed to address the copyright protection of digital materials.…

While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to…

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…