融合光影敏感特征及K-A表示定理的AI生成图像鉴别方法

邓巧; 姜林; 刘乐新; 唐吕鑫; 杨英丽

doi:10.12263/DZXB.20250250

您当前的位置：

首页 >

文章列表页 >

融合光影敏感特征及K-A表示定理的AI生成图像鉴别方法

学术论文 | 更新时间：2026-02-10

- 融合光影敏感特征及K-A表示定理的AI生成图像鉴别方法
- AI-Generated Image Detection Method Integrating Light-Shadow Sensitive Features and Kolmogorov-Arnold Representation Theorem
- 电子学报 2025年53卷第11期页码：4077-4090
- 作者机构：
  
  1.湖南工商大学人工智能与先进计算学院，湖南长沙 410000
  2.湘江实验室，湖南长沙 410000
- 作者简介：
  
  [ "邓巧女，2004年11月出生于湖南省衡阳市.现为湖南工商大学人工智能与先进计算学院（湘江书院）本科生.主要研究方向为计算机视觉.E-mail: 1529776271@qq.com" ]
  [ "姜林男，1977年11月出生于湖南省常德市.现为湖南工商大学人工智能与先进计算学院（湘江书院）教授.主要研究方向为智能语音处理、机器视觉、机器人应用.E-mail: jlcdf@163.com" ]
  [ "刘乐新男，2004年1月出生于湖南省益阳市.现为湖南工商大学人工智能与先进计算学院（湘江书院）本科生.主要研究方向为计算机视觉. E-mail: 207264603@qq.com" ]
  [ "唐吕鑫男，2005年2月出生于湖南省长沙市.现为湖南工商大学人工智能与先进计算学院（湘江书院）本科生.主要研究方向为计算机视觉.E-mail: 3186221452@qq.com" ]
  [ "杨英丽女，2005年3月出生于江西省九江市.现为湖南工商大学人工智能与先进计算学院（湘江书院）本科生.主要研究方向为计算机视觉.E-mail: 2307225478@qq.com" ]
- 基金信息：
  
  湖南省教育厅科学研究项目（重点）(22A0441);湘江实验室重大项目(23XJ01003;23XJ01009)
- DOI：10.12263/DZXB.20250250
  中图分类号： TP391;
- 收稿：2025-04-02，
  
  录用：2025-05-22，
  
  纸质出版：2025-11-25
- 稿件说明：
移动端阅览
邓巧, 姜林, 刘乐新, 等. 融合光影敏感特征及K-A表示定理的AI生成图像鉴别方法[J]. 电子学报, 2025, 53(11): 4077-4090.

DENG Qiao, JIANG Lin, LIU Le-xin, et al. AI-Generated Image Detection Method Integrating Light-Shadow Sensitive Features and Kolmogorov-Arnold Representation Theorem[J]. Acta Electronica Sinica, 2025, 53(11): 4077-4090.
邓巧, 姜林, 刘乐新, 等. 融合光影敏感特征及K-A表示定理的AI生成图像鉴别方法[J]. 电子学报, 2025, 53(11): 4077-4090. DOI：10.12263/DZXB.20250250

DENG Qiao, JIANG Lin, LIU Le-xin, et al. AI-Generated Image Detection Method Integrating Light-Shadow Sensitive Features and Kolmogorov-Arnold Representation Theorem[J]. Acta Electronica Sinica, 2025, 53(11): 4077-4090. DOI：10.12263/DZXB.20250250

摘要

人工智能（Artificial Intelligence，AI）生成图像技术发展迅猛，高逼真内容对网络安全与社会信任构成重大威胁，而人类自主鉴别准确率仅约59%，接近随机猜测水平.现有检测方法普遍存在性能有限、跨模型泛化能力不足等问题，尤其无法有效捕捉生成图像中物理光照的不一致性.为此，本文提出融合光影敏感特征及Kolmogorov-Arnold（K-A）表示定理的特征融合鉴别方法（Light-enhanced Kolmogorov-Arnold Networks，L-KAN）.在红绿蓝三原色（Red、Green、Blue，RGB）语义特征、频域特征和边缘特征的基础上，构建光影敏感特征.该特征通过整体光照分布、阴影面积及方向和多尺度光照梯度特性，捕捉生成图像中的光照异常.引入K-A表示定理进行特征融合，通过内外层函数协同作用，在保证特征互补性的同时有效抑制特征冗余.在3组公开数据集上，与9种先进方法进行对比，所提方法平均分类准确率均有显著提升.

Abstract

The rapid advancement of artificial intelligence (AI)-generated image technologies poses significant threats to cybersecurity and public trust

as human visual detection accuracy remains as low as 59%

close to random guessing. Existing detection methods suffer from limited performance and poor generalization across generative models

particularly struggling to capture physical inconsistencies in illumination. To address this gap

we propose L-KAN (Light-enhanced Kolmogorov-Arnold Networks)

a novel detection framework that integrates illumination-sensitive features with the Kolmogorov-Arnold (K-A) representation theorem. Building upon red-green-blue (RGB) semantics

frequency-domain cues

and edge information

we construct physically grounded features that encode global illumination distribution

shadow geometry

and multi-scale illumination gradients to expose lighting inconsistencies in synthetic images. Leveraging the K-A theorem for feature fusion

ours method synergizes inner and outer functions to enhance feature complementarity while suppressing redundancy. Experimental results on three public datasets demonstrate that L-KAN achieves a competitive performance compared with the state of the art methods.

关键词

Keywords

references

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .

HO J , JAIN A , ABBEEL P . Denoising diffusion probabilistic models [J ] . Advances in Neural Information Processing Systems , 2020 , 33 : 6840 - 6851 .

KARRAS T , AITTALA M , LAINE S , et al . Alias-free generative adversarial networks [J ] . Advances Inneural Information Processing Systems , 2021 , 34 : 852 - 863 .

KOUTLIS C , PAPADOPOULOS S . Leveraging representations from intermediate encoder-blocks for synthetic image detection [M ] // Computer Vision-ECCV 2024 . Cham : Springer Nature Switzerland , 2024 : 394 - 411 .

WESTERLUND M . The emergence of deepfake technology: A review [J ] . Technology Innovation Management Review , 2019 , 9 ( 11 ): 39 - 52 .

MANDELLI S , BONETTINI N , BESTAGINI P , et al . Detecting Gan-generated images by orthogonal training of multiple CNNs [C ] // 2022 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2022 : 3091 - 3095 .

朱世强 , 王永恒 . 基于人工智能的内容安全发展战略研究 [J ] . 中国工程科学 , 2021 , 23 ( 3 ): 67 - 74 .

ZHU S Q , WANG Y H . Development of content security based on artificial intelligence [J ] . Strategic Study of CAE , 2021 , 23 ( 3 ): 67 - 74 . (in Chinese)

NIGHTINGALE S J , FARID H . AI-synthesized faces are indistinguishable from real faces and more trustworthy [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2022 , 119 ( 8 ): e2120481119 .

谢天 , 于灵云 , 罗常伟 , 等 . 深度人脸伪造与检测技术综述 [J ] . 清华大学学报(自然科学版) , 2023 , 63 ( 9 ): 1350 - 1365 .

XIE T , YU L Y , LUO C W , et al . Survey of deep face manipulation and fake detection [J ] . Journal of Tsinghua University (Science and Technology) , 2023 , 63 ( 9 ): 1350 - 1365 . (in Chinese)

ZHAO T C , XU X , XU M Z , et al . Learning self-consistency for deepfake detection [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2021 : 15003 - 15013 .

QIAN Y Y , YIN G J , SHENG L , et al . Thinking in frequency: Face forgery detection by mining frequency-aware clues [M ] // Computer Vision - ECCV 2020 . Cham : Springer International Publishing , 2020 : 86 - 103 .

GRAGNANIELLO D , MARRA F , POGGI G , et al . Analysis of adversarial attacks against CNN-based image forgery detectors [C ] // 2018 26th European Signal Processing Conference (EUSIPCO) . Piscataway : IEEE , 2018 : 967 - 971 .

VERDOLIVA L . Media forensics and DeepFakes: An overview [J ] . IEEE Journal of Selected Topics in Signal Processing , 2020 , 14 ( 5 ): 910 - 932 .

SZEGEDY C , LIU W , JIA Y Q , et al . Going deeper with convolutions [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 1 - 9 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .

RONNEBERGER O , FISCHER P , BROX T . U-Net: Convolutional networks for biomedical image segmentation [M ] // Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 . Cham : Springer International Publishing , 2015 : 234 - 241 .

HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 .

WANG S Y , WANG O , ZHANG R , et al . CNN-generated images are surprisingly easy to spot for now [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 8695 - 8704 .

TAN C , ZHAO Y , WEI S , et al . Learning on gradients: Generalized artifacts representation for gan-generated images detection [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 12105 - 12114 .

OJHA U , LI Y H , LEE Y J . Towards universal fake image detectors that generalize across generative models [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2023 : 24480 - 24489 .

TAN C C , LIU H , ZHAO Y , et al . Rethinking the up-sampling operations in CNN-based generative network for generalizable deepfake detection [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2024 : 28130 - 28139 .

FRANK J , EISENHOFER T , SCHÖNHERR L , et al . Leveraging frequency analysis for deep fake image recognition [C ] // International Conference on Machine Learning . San Diego : PMLR , 2020 : 3247 - 3258 .

TAN C C , ZHAO Y , WEI S K , et al . Frequency-aware deepfake detection: Improving generalizability through frequency space learning [EB/OL ] . ( 2024-05-12 )[ 2025-06-05 ] . https://arxiv.org/abs/2403.07240v1 https://arxiv.org/abs/2403.07240v1 .

DURALL R , KEUPER M , KEUPER J . Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 7887 - 7896 .

LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 936 - 944 .

刘兵 , 李穗 , 刘明明 , 等 . 基于条件变分推断与内省对抗学习的多样化图像描述生成 [J ] . 电子学报 , 2024 , 52 ( 7 ): 2219 - 2227 .

LIU B , LI S , LIU M M , et al . Diverse image captioning via conditional variational inference and introspective adversarial learning [J ] . Acta Electronica Sinica , 2024 , 52 ( 7 ): 2219 - 2227 . (in Chinese)

张帅勇 , 刘美琴 , 姚超 , 等 . 分级特征反馈融合的深度图像超分辨率重建 [J ] . 自动化学报 , 2022 , 48 ( 4 ): 992 - 1003 .

ZHANG S Y , LIU M Q , YAO C , et al . Hierarchical feature feedback network for depth super-resolution reconstruction [J ] . Acta Automatica Sinica , 2022 , 48 ( 4 ): 992 - 1003 . (in Chinese)

林知心 , 郑玉棒 , 马天宇 , 等 . 基于轻量级全连接张量映射网络的高光谱图像分类方法 [J ] . 电子学报 , 2024 , 52 ( 10 ): 3541 - 3551 .

LIN Z X , ZHENG Y B , MA T Y , et al . Lightweight fully-connected tensorial mapping network for hyperspectral image classification [J ] . Acta Electronica Sinica , 2024 , 52 ( 10 ): 3541 - 3551 . (in Chinese)

WILSON J , NICKISCH H , RÄTSCH G . Deep kernel learning [C ] // International Conference on Artificial Intelligence and Statistics . New York : PMLR , 2020 : 370 - 378 .

SYSKO-ROMAńCZUK S , STRISOVSZKY J , LUTSIV N . A representer theorem for deep kernel learning [J ] . Joursnal of Machine Learning Research , 2022 , 23 ( 1 ): 1 - 32 .

乔通 , 陈彧星 , 谢世闯 , 等 . 多色彩通道特征融合的GAN合成图像检测方法 [J ] . 电子学报 , 2024 , 52 ( 3 ): 924 - 936 .

QIAO T , CHEN Y X , XIE S C , et al . GAN synthetic image detection using fused features in the multi-color channels [J ] . Acta Electronica Sinica , 2024 , 52 ( 3 ): 924 - 936 . (in Chinese)

KOLMOGOROV A N . On the Representation of Continuous Functions of Several Variables by Superpositions of Continuous Functions of a Smaller Number of Variables [M ] . Providence : American Mathematical Society , 1961 .

SCHMIDT-HIEBER J . The Kolmogorov-Arnold representation theorem revisited [J ] . Neural Networks , 2021 , 137 : 119 - 126 .

POLAR A , POLUEKTOV M . A deep machine learning algorithm for construction of the Kolmogorov-Arnold representation [J ] . Engineering Applications of Artificial Intelligence , 2021 , 99 : 104137 .

LIU Z , WANG Y , VAIDYA S , et al . Kan: Kol-mogorov-arnold networks [EB/OL ] . ( 2025-02-02 )[ 2025-06-05 ] . https://arxiv.org/pdf/2408.02950 https://arxiv.org/pdf/2408.02950 .

AGARWAL R , MELNICK L , FROSST N , et al . Neural additive models: Interpretable machine learning with neural nets [J ] . Advances in Neural Information Processing Systems , 2021 , 34 : 4699 - 4711 .

GOODFELLOW I , BENGIO Y , COURSVILLE A , et al . Deep Learning [M ] . Cambridge : MIT press , 2016 .

LI J M , XIE H T , LI J H , et al . Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 6454 - 6463 .

KARRAS T , AILA T M , LAINE S , et al . Progressive growing of GANs for improved quality, stability, and variation [EB/OL ] . ( 2018-02-26 )[ 2025-06-05 ] . https://arxiv.org/abs/1710.10196v3 https://arxiv.org/abs/1710.10196v3 .

YU F , ZHANG Y D , SONG S R , et al . Construction of a large-scale image dataset using deep learning with humans in the loop [EB/OL ] . ( 2016-06-04 )[ 2025-06-05 ] . https://arxiv.org/abs/1506.03365 https://arxiv.org/abs/1506.03365 .

PARK T , LIU M Y , WANG T C , et al . Semantic image synthesis with spatially-adaptive normalization [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 2337 - 2346 .

CHOI Y , CHOI M , KIM M , et al . StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 8789 - 8797 .

ROSSLER A , COZZOLINO D , VERDOLIVA L , et al . FaceForensics++: Learning to detect manipulated facial images [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2019 : 1 - 11 .

RUSSAKOVSKY O , DENG J , SU H , et al . ImageNet large scale visual recognition challenge [J ] . International Journal of Computer Vision , 2015 , 115 ( 3 ): 211 - 252 .

LIU Z W , LUO P , WANG X G , et al . Deep learning face attributes in the wild [C ] // 2015 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2015 : 3730 - 3738 .

LIN T Y , MAIRE M , BELONGIE S , et al . Microsoft COCO: Common objects in context [M ] // Computer Vision-ECCV 2014 . Cham : Springer International Publishing , 2014 : 740 - 755 .

BELLEMARE M G , DANIHELKA I , DABNEY W , et al . The Cramer distance as a solution to biased Wasserstein gradients [EB/OL ] . ( 2017-05-30 )[ 2025-06-05 ] . https://arxiv.org/abs/1705.10743v1 https://arxiv.org/abs/1705.10743v1 .

LI C L , CHANG W C , CHENG Y , et al . MMD GAN: Towards deeper understanding of moment matching network [EB/OL ] . ( 2017-11-27 )[ 2025-06-05 ] . https://arxiv.org/abs/1705.08584 https://arxiv.org/abs/1705.08584 .

NIE W L , NARODYTSKA N , PATEL A B . RelGAN: Relational generative adversarial networks for text generation [C ] // International Conference on Learning Representations . Washington : ICLR , 2018 : 1 .

LIU M , DING Y K , XIA M , et al . STGAN: A unified selective transfer network for arbitrary image attribute editing [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 3668 - 3677 .

ROMBACH R , BLATTMANN A , LORENZ D , et al . High-resolution image synthesis with latent diffusion models [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 10674 - 10685 .

RUSKOV M . Grimm in wonderland: Prompt engineering with midjourney to illustrate fairytales [EB/OL ] . ( 2023-08-25 )[ 2025-06-05 ] . https://arxiv.org/abs/2302.08961v2 https://arxiv.org/abs/2302.08961v2 .

GU S Y , CHEN D , BAO J M , et al . Vector quantized diffusion model for text-to-image synthesis [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 10686 - 10696 .

NICHOL A , DHARIWAL P , RAMESH A , et al . GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models [EB/OL ] . ( 2022-03-28 )[ 2025-06-05 ] . https://arxiv.org/abs/2112.10741v3 https://arxiv.org/abs/2112.10741v3 .

SHIOHARA K , YAMASAKI T . Detecting deepfakes with self-blended images [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2022 : 18699 - 18708 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向在线连续学习的特征融合引导的梯度重加权算法

面向时序异常检测的可变视距多向扫描方法

结合特征融合增强和细节特征的低照度小目标检测方法

基于EIMYOLO的高分遥感图像目标检测

InP掺杂超晶格的MOCVD生长与表征