Related papers: Diff-Cleanse: Identifying and Mitigating Backdoor …
Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…
In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…
Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via progressive noise-addition and denoising. To gain a better…
Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models…
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However, they are vulnerable to backdoor attacks as reported by…
Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor…
Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they…
Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…
In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and…
Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image…
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…
Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the…
Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques, primarily designed…
The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…
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…
Diffusion models are powerful generative models in continuous data domains such as image and video data. Discrete graph diffusion models (DGDMs) have recently extended them for graph generation, which are crucial in fields like molecule and…
Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger.…
Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects…
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…