中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Artifact feature purification for cross-domain detection of AI-generated images

文献类型：期刊论文

作者Meng, Zheling1,2,3; Peng, Bo1; Dong, Jing1,2,3; Tan, Tieniu1,2,3; Cheng, Haonan4
刊名COMPUTER VISION AND IMAGE UNDERSTANDING
出版日期2024-10-01
卷号247页码:11
关键词AI-generated image detection Cross-domain Artifact Purification
ISSN号1077-3142
DOI10.1016/j.cviu.2024.104078
通讯作者Dong, Jing(jdong@nlpr.ia.ac.cn)
英文摘要In the era of AIGC, the fast development of visual content generation technologies, such as diffusion models, brings potential security risks to our society. Existing generated image detection methods suffer from performance drops when faced with out-of-domain generators and image scenes. To relieve this problem, we propose Artifact Purification Network (APN) to facilitate the artifact extraction from generated images through the explicit and implicit purification processes. For the explicit one, a suspicious frequency-band proposal method and a spatial feature decomposition method are proposed to extract artifact-related features. For the implicit one, a training strategy based on mutual information estimation is proposed to further purify the artifact-related features. The experiments are conducted in two settings. Firstly, we perform a cross-generator evaluation, wherein detectors trained using data from one generator are evaluated on data generated by other generators. Secondly, we conduct a cross-scene evaluation, wherein detectors trained for a specific domain of content (e.g., ImageNet) are assessed on data collected from another domain (e.g., LSUN-Bedroom). Results show that for cross-generator detection, the average accuracy of APN is 5.6% . 6% similar to 16.4% . 4% higher than the previous 11 methods on the GenImage dataset and 1.7% . 7% similar to 50.1% . 1% on the DiffusionForensics dataset. For cross-scene detection, APN maintains its high performance. Via visualization analysis, we find that the proposed method can extract diverse forgery patterns and condense the forgery information diluted in irrelated features. We also find that the artifact features APN focuses on across generators and scenes are global and diverse. The code will be available at https://github.com/RichardSunnyMeng/APN-official-codes.
资助项目National Key Research and Development Program of China[2021YFC3320103] ; National Natural Science Foundation of China (NSFC)[62272460] ; Beijing Natural Science Foundation[4232037] ; Open Research Project of the State Key Laboratory of Media Convergence and Communication, Communication University of China, China[SKLMCC2022KF002]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001286112400001
出版者ACADEMIC PRESS INC ELSEVIER SCIENCE
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC) ; Beijing Natural Science Foundation ; Open Research Project of the State Key Laboratory of Media Convergence and Communication, Communication University of China, China
源URL[http://ir.ia.ac.cn/handle/173211/59285]  
专题多模态人工智能系统全国重点实验室
自动化研究所_智能感知与计算研究中心
通讯作者Dong, Jing
作者单位1.Chinese Acad Sci, Inst Automat, New Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Commun Univ China, State Key Lab Media Convergence & Commun, Beijing 100024, Peoples R China
推荐引用方式
GB/T 7714		 Meng, Zheling,Peng, Bo,Dong, Jing,et al. Artifact feature purification for cross-domain detection of AI-generated images[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2024,247:11.
APA Meng, Zheling,Peng, Bo,Dong, Jing,Tan, Tieniu,&Cheng, Haonan.(2024).Artifact feature purification for cross-domain detection of AI-generated images.COMPUTER VISION AND IMAGE UNDERSTANDING,247,11.
MLA Meng, Zheling,et al."Artifact feature purification for cross-domain detection of AI-generated images".COMPUTER VISION AND IMAGE UNDERSTANDING 247(2024):11.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。