Related papers: PersGuard: Preventing Malicious Personalization vi…

Text-to-Image (T2I) diffusion models have demonstrated strong generation ability, but their potential to generate unsafe content raises significant safety concerns. Existing inference-time defense methods typically perform category-agnostic…

Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem. Previous solutions, such as Anti-DreamBooth, add adversarial noise to images to protect…

Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration methods have shown promising results compared to traditional…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level…

Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to…

The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models…

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…

This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Recent advances in large-scale text-to-image (T2I) diffusion models have enabled a variety of downstream applications, including style customization, subject-driven personalization, and conditional generation. As T2I models require…

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Person Re-Identification (ReID) systems pose a significant security risk from backdoor attacks, allowing adversaries to evade tracking or impersonate others. Beyond recognizing this issue, we investigate how backdoor attacks can be deployed…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…