Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Liang, Chumeng"'
Autor:
Liang, Chumeng, You, Jiaxuan
Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets of diffus
Externí odkaz:
http://arxiv.org/abs/2410.03640
Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist
Externí odkaz:
http://arxiv.org/abs/2403.11162
Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized diffusion custo
Externí odkaz:
http://arxiv.org/abs/2310.04687
While generative diffusion models excel in producing high-quality images, they can also be misused to mimic authorized images, posing a significant threat to AI systems. Efforts have been made to add calibrated perturbations to protect images from di
Externí odkaz:
http://arxiv.org/abs/2311.12832
This paper proposes the fine-grained traffic prediction task (e.g. interval between data points is 1 minute), which is essential to traffic-related downstream applications. Under this setting, traffic flow is highly influenced by traffic signals and
Externí odkaz:
http://arxiv.org/abs/2306.10945
Autor:
Liang, Chumeng, Wu, Xiaoyu
Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by imitating
Externí odkaz:
http://arxiv.org/abs/2305.12683
Autor:
Liang, Chumeng, Wu, Xiaoyu, Hua, Yang, Zhang, Jiaru, Xue, Yiming, Song, Tao, Xue, Zhengui, Ma, Ruhui, Guan, Haibing
Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright
Externí odkaz:
http://arxiv.org/abs/2302.04578
Autor:
Liang, Chumeng, Huang, Zherui, Liu, Yicheng, Liu, Zhanyu, Zheng, Guanjie, Shi, Hanyuan, Wu, Kan, Du, Yuhao, Li, Fuliang, Li, Zhenhui
Traffic simulation provides interactive data for the optimization of traffic control policies. However, existing traffic simulators are limited by their lack of scalability and shortage in input data, which prevents them from generating interactive d
Externí odkaz:
http://arxiv.org/abs/2210.00896
Autor:
Gianmarco De Francisci Morales, Claudia Perlich, Natali Ruchansky, Nicolas Kourtellis, Elena Baralis, Francesco Bonchi
The multi-volume set LNAI 14169 until 14175 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023, which took place in Turin, Italy, in September 2023.The 196 papers w