While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to backdoor attacks, but …
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training …
Y Liu, R Chen, L Sun - arXiv preprint arXiv:2406.18944, 2024 - arxiv.org
Personalized diffusion models have gained popularity for adapting pre-trained text-to-image models to generate images of specific topics with only a few images. However, recent …
MA Merzouk, E Beurier, R Yaich… - arXiv preprint arXiv …, 2024 - arxiv.org
The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples …
Z Guo, J Liu - arXiv preprint arXiv:2311.09680, 2023 - arxiv.org
The rapid progress of Large Models (LMs) has recently revolutionized various fields of deep learning with remarkable grades, ranging from Natural Language Processing (NLP) to …
Backdoor defense is crucial to ensure the safety and robustness of machine learning models when under attack. However, most existing methods specialize in either the detection or …
In adversarial defense, adversarial purification can be viewed as a special generation task with the purpose to remove adversarial attacks and diffusion models excel in adversarial …