Related papers: PureDiffusion: Using Backdoor to Counter Backdoor …

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vulnerability to backdoor attacks. Existing attack methods…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

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 are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Diffusion models are state-of-the-art deep learning generative models that are trained on the principle of learning forward and backward diffusion processes via the progressive addition of noise and denoising. In this paper, we aim to fool…

Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase. Pre-processing-based defense, which is one of the…

Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manifolds. However, even with their increasing industrial…

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential…

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…

The increasing use of generative models such as diffusion models for synthetic data augmentation has greatly reduced the cost of data collection and labeling in downstream perception tasks. However, this new data source paradigm may…

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

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…

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…

Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees,…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and plagiarism. Existing countermeasures largely rely on…