Related papers: Targeted Attack Improves Protection against Unauth…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box targeted attacks, which gives a rigorous theoretical…

Denoising probabilistic diffusion models have shown breakthrough performance to generate more photo-realistic images or human-level illustrations than the prior models such as GANs. This high image-generation capability has stimulated the…

Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security risks, including deepfakes and copyright infringement. In…

Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their…

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this…

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…

Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing…

Recent advances in diffusion models have enabled powerful image editing capabilities guided by natural language prompts, unlocking new creative possibilities. However, they introduce significant ethical and legal risks, such as deepfakes…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Morphed face images have recently become a growing concern for existing face verification systems, as they are relatively easy to generate and can be used to impersonate someone's identity for various malicious purposes. Efficient Morphing…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…

Model customization introduces new concepts to existing text-to-image models, enabling the generation of these new concepts/objects in novel contexts. However, such methods lack accurate camera view control with respect to the new object,…

Robust invisible watermarking schemes aim to embed hidden information into images such that the watermark survives common manipulations. However, powerful diffusion-based image generation and editing techniques now pose a new threat to…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…