Detection of GAN-generated Fake Images over Social Networks. MIPR, 2018.
Francesco Marra, Diego Gragnaniello, Davide Cozzolino, Luisa Verdoliva.
核心思想：GAN discriminator，Steganalysis features，CNN networks
Detecting and Simulating Artifacts in GAN Fake Images. WIFS, 2019.
Xu Zhang, Svebor Karaman, and Shih-Fu Chang. USA
核心思想：基于GAN上采样产生的的频域独特伪影，使用灰盒AutoGAN生成fake image
Incremental learning for the detection and classification of GAN-generated images. WIFS, 2019.
Francesco Marra, Cristiano Saltori†, Giulia Boato and Luisa Verdoliva. Italy
核心思想：增量学习
Detecting GAN generated Fake Images using Co-occurrence Matrices. Electronic Imaging, 2019.
Nataraj, Lakshmanan; Mohammed, Tajuddin Manhar; Manjunath, B. S.; Chandrasekaran, Shivkumar; Flenner, Arjuna; Bappy, Jawadul H.; Roy-Chowdhury, Amit K
核心思想：RGB三通道的共生矩阵作为分类特征
CNN-generated images are surprisingly easy to spot…for now. CVPR, 2020.
Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, Alexei A. Efros.
核心思想：将数据增强添加至检测分类器，全面测试泛化性。
Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions. CVPR, 2020.
Ricard Durall, Margret Keuper, Janis Keuper.
核心思想：up-convolution操作无法复制真实图像频谱，基于此发现设计简单的检测方法。
Fourier Spectrum Discrepancies in Deep Network Generated Images. NeurIPS, 2020.
Tarik Dzanic, Karan Shah, Freddie Witherden.
核心思想：基于DFT的高频信号，在高分辨率/低压缩率的情况下频谱特征更加容易区分。
Leveraging Frequency Analysis for Deep Fake Image Recognition. ICML, 2020.
Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz.
核心思想：基于DFT频域分析，同上篇文章
T-GD: Transferable GAN-generated Images Detection Framework. ICML 2020.
Hyeonseong Jeon, Youngoh Bang, Junyaup Kim, Simon S. Woo.
核心思想：使用教师——学生模型，self-training半监督学习
On the use of Benford’s law to detect GAN-generated images
N. Bonettini, P. Bestagini, S. Milani, and S. Tubaro. ICPR, 2020.
核心思想：使用本福特定律相关特征+随机森林
GAN-Generated Image Detection With Self-Attention Mechanism Against GAN Generator Defect. IEEE Journal of Selected Topics in Signal Processing, 2020.
Zhongjie Mi, Xinghao Jiang, Tanfeng Sun, and Ke Xu.
核心思想：自注意力机制
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis. IJCAI, 2021.
Yang He, Ning Yu, Margret Keuper, Mario Fritz
核心思想：使用去噪等图像再生成的方式得到残差，使用二分类器完成检测
A closer look at fourier spectrum discrepancies for cnn-generated images detection. CVPR, 2021.
Keshigeyan Chandrasegaran, Ngoc-Trung Tra, Ngai-Man Cheung. SUTD
核心思想：频谱差异&最后一个上采样操作
Are GAN generated images easy to detect? A critical analysis of the state-of-the-art. ICME, 2021.
D. Gragnaniello, D. Cozzolino, F. Marra, G. Poggi and L. Verdoliva.
核心思想：总结性文章
Detection of GAN-Generated Images by Estimating Artifact Similarity. SPL, 2021.
Weichuang Li, Peisong He, et al.
核心思想：对于生成图像和真实图像分别构建参考特征，然后分别比较测试图像特征与二个参考特征，根据相似度分数进行检测
Detection, Attribution and Localization of GAN Generated Images. arXiv 2021.
M Goebel，L Nataraj，T Nanjundaswamy，TM Mohammed，BS Manjunath
核心思想：将图像三通道共现矩阵输入XceptionNet变体
Think Twice Before Detecting GAN-generated Fake Images from their Spectral Domain Imprints CVPR 2022
Chengdong Dong, Ajay Kumar, Eryun Liu
核心思想：针对基于频域特征检测方法的对抗，使用DFT和IDFT
Detecting Generated Images by Real Images. ECCV, 2022.
Bo Liu, Fan Yang, Xiuli Bi, Bin Xiao, Weisheng Li, Xinbo Gao.
核心思想：利用真实图像特有的噪声模式，设计简单分类器完成检测。
FingerprintNet: Synthesized Fingerprints for Generated Image Detection. ECCV, 2022.
Yonghyun Jeong, Doyeon Kim, Youngmin Ro, Pyounggeon Kim, and Jongwon Choi.
核心思想：使用real生成synthesized图像，然后用于训练分类器
Discovering Transferable Forensic Features for CNN-Generated Images Detection. ECCV 2022.
Singapore University of Technology and Design
核心思想：利用图像的颜色信息，进行针对性地数据增强
BiHPF: bilateral high pass filters for robust deepfake detection. WACV, 2022.
Jeong, Y., Kim, D., Min, S., Joe, S., Gwon, Y., Choi, J.
核心思想：使用对抗训练的方式得到图像的伪影压缩图，证实artifact的存在，后使用双边高通滤波（像素域&频域）放大频域伪影送入分类器检测。
Fusing Global and Local Features for Generalized AI-Synthesized Image Detection. ICIP 2022
Yan Ju, Shan Jia, Lipeng Ke, Hongfei Xue, Koki Nagano, Siwei Lyu.
核心思想：使用ResNet，提全局特征和local patches的特征，融合之后分类检测
GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection. IEEE Transactions on Multimedia, 2023.
Yan Ju, Shan Jia, Jialing Cai, Haiying Guan, Siwei Lyu.
核心思想：ICIP 2022 那篇的扩充版本
Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection. CVPR, 2023.
Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Yunchao Wei.
核心思想：利用梯度信息，检测GAN生成的图像
Towards Universal Fake Image Detectors that Generalize Across Generative Models. CVPR, 2023.
Utkarsh Ojha, Yuheng Li, Yong Jae Lee.
核心思想：使用CLIP提特征，然后基于此特征完成检测（1）分类器；（2）基于特征之间的距离
De-fake: Detection and attribution of fake images generated by text-to-image generation models. CCS, 2023.
Zeyang Sha, Zheng Li, Ning Yu, Yang Zhang.
核心思想：主要利用提示词与对应图像的距离，设计简单分类器完成检测。
DIRE for Diffusion-Generated Image Detection. ICCV, 2023.
Zhendong Wang, Jianmin Bao, Wengang Zhou, Weilun Wang, Hezhen Hu, Hong Chen, Houqiang Li.
核心思想：利用真实图像与合成图像重建前后的残差差异
Online Detection of AI-Generated Images. ICCV Workshop, 2023.
David C. Epstein, Ishan Jain, Oliver Wang, Richard Zhang.
核心思想：不仅探究了AIGC检测方法的泛化性，而且还测试了基于AI的图像篡改检测与定位的性能，实现了像素级的AIGC检测。
Detecting Images Generated by Deep Diffusion Models Using Their Local Intrinsic Dimensionality. ICCV Workshop, 2023.
Peter Lorenz, Ricard L. Durall, Janis Keuper.
核心思想：利用对抗样本检测中常用的Local Intrinsic Dimensionality手段，检测AIGC图像。
On The Detection of Synthetic Images Generated by Diffusion Models. ICASSP, 2023
Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva…
核心思想：意大利LV团队做的，基于频域分析
Exposing fake images generated by text-to-image diffusion models. PRL, 2023.
Qiang Xu, Hao Wang, Laijin Meng, Zhongjie Mi, Jianye Yuan, Hong Yan.
核心思想：基于注意力机制的特征提取和基于ViT的特征提取，baselines主要选取的是针对自然图像和电脑生成图像的检测方法。
Intriguing properties of synthetic images: from generative adversarial networks to diffusion models. CVPR Workshop, 2023.
Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva.
核心思想：意大利LV团队做的，基于频域分析
Synthbuster: Towards Detection of Diffusion Model Generated Images. IEEE Open Journal of Signal Processing, 2023.
Quentin Bammey.
核心思想：高通滤波得到图像残差，然后经傅立叶变换得到频谱图，送入分类器检测。
Disentangling Different Levels of GAN Fingerprints for Task-specific Forensics. Computer Standards & Interfaces, 2023.
Chi Liu, Tianqing Zhu, Yuan Zhao, Jun Zhang, Wanlei Zhou.
核心思想：分别提取空域和频域的特征，用于不同类型的取证任务。
Improving Synthetically Generated Image Detection in Cross-Concept Settings. MAD Workshop 2023.
Pantelis Dogoulis, Giorgos Kordopatis-Zilos, Ioannis Kompatsiaris, Symeon Papadopoulos
核心思想：使用图像质量评价，选择生成图像训练集的子集，与真实图像一起送入ResNet
AI-Generated Image Detection using a Cross-Attention Enhanced Dual-Stream Network. APSIPA ASC, 2023.
Ziyi Xi, Wenmin Huang, Kangkang Wei, Weiqi Luo and Peijia Zheng.
核心思想：基于交叉注意力的双流检测网络；residual stream + content stream; cross-attention; feature fusion
Generalizable Synthetic Image Detection via Language-guided Contrastive Learning. arXiv, 2023.
Haiwei Wu, Jiantao Zhou, and Shile Zhang.
核心思想：设计图像文本对，基于对比学习损失微调CLIP的image encoder和text encoder，使得虚假图像特征更接近“fake photo”提示文本特征。
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors. arXiv 2023.
You-Ming Chang, Chen Yeh, Wei-Chen Chiu, Ning Yu.
核心思想：针对指定的instruction“Is this photo real S*”，训练LLM tokenizer和Q-former tokenizer对S*的表示，并获得检测结果。
Detecting Generated Images by Real Images Only. arXiv 2023.
Xiuli Bi, Bo Liu, Fan Yang, Bin Xiao, Weisheng Li, Gao Huang, Pamela C. Cosman.
核心思想：把AIGC检测看成新颖点检测任务，训练一个基于正样本的单分类器。
Diffusion Noise Feature: Accurate and Fast Generated Image Detection. arXiv 2023.
Yichi Zhang, Xiaogang Xu.
核心思想：通过寻找diffusion模型生成图像中特有的噪声模式进行检测。
GenDet: Towards Good Generalizations for AI-Generated Image Detection. arXiv 2023.
Mingjian Zhu, Hanting Chen, Mouxiao Huang, Wei Li, Hailin Hu, Jie Hu, Yunhe Wang.
核心思想：基于教师学生模型的异常检测
LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection
Yunpeng Luo, Junlong Du, Ke Yan, Shouhong Ding. CVPR, 2024.
核心思想：对DIRE的改进，基于潜空间重建损失，提高检测效率
DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection
Yewon Lim, Changyeon Lee, Aerin Kim, Oren Etzioni. ICML Workshop, 2024.
核心思想：对DIRE的改进，使用知识蒸馏提高检测效率
Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection
Chuangchuang Tan, Huan Liu, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei. CVPR, 2024.
核心思想：基于上采样的痕迹特征，Neighboring Pixel Relationships（NPR）
Shadows Don’t Lie and Lines Can’t Bend! Generative Models don’t know Projective Geometry…for now
Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D.A. Forsyth, Anand Bhattad. CVPR, 2024.
核心思想：使用影射几何学特征，比如影子，透视场和线段
Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection
Huan Liu, Zichang Tan, Chuangchuang Tan, Yunchao Wei, Yao Zhao, Jingdong Wang. CVPR, 2024.
核心思想：FatFormer像素域+频域伪造特征融合，使用语义引导模块提升泛化性
FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion
George Cazenavette, Avneesh Sud, Thomas Leung Ben Usman. CVPR, 2024.
核心思想：原始图像、解码噪声、解码重建图像一同送入ResNet进行分类
AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error
Jonas Ricker, Denis Lukovnikov, and Asja Fischer. CVPR, 2024.
核心思想：也是基于重建损失，自编码器，使用lpips值作为衡量指标
Raising the Bar of AI-generated Image Detection with CLIP
Davide Cozzolino, Giovanni Poggi, Riccardo Corvi, Matthias Nießner, Luisa Verdoliva. CVPR Workshop, 2024.
核心思想：使用CLIP提特征，然后使用简单的SVM对特征进行分类。
MaskSim: Detection of synthetic images by masked spectrum similarity analysis
Li et al. CVPR Workshops, 2024. France/Brazil/Hongkong
核心思想：首先使用去噪网络DnCNN（Zhang 等，2017）对图像进行预处理，然后对降噪图像进行DFT变换得到频谱图，并设计可训练掩码，关注频谱图中对区分自然图像和生成图像贡献最大的频率，得到增强频谱。之后，使用可训练参考频谱使得提取出的增强频谱更加准确。最后，通过计算参考频谱与增强频谱的相似性训练逻辑回归分类器完成检测。
Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks
Romeo Lanzino, Federico Fontana, Anxhelo Diko, Marco Raoul Marini, Luigi Cinque. CVPR Workshops, 2024.
核心思想：使用FFT频域特征和LBP纹理特征以及RGB整体特征域三路，二值神经网络BNN
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Domain Learning. AAAI, 2024. (FreqNet)
Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei
核心思想：仅使用图像的高频特征完成检测，并针对性修改分类器，使其关注高频特征部分
DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images ICML 2024
Baoying Chen et al. 阿里巴巴 & 中山大学
核心思想：首先得到真实图像和虚假图像各自的重建图像，然后基于真实、真实重建、虚假、虚假重建这4类图像，使用对比学习损失训练分类器，得到更加准确的决策边界。
Exposing the Fake: Effective Diffusion-Generated Images Detection (SeDID)
Ruipeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, Kaidi Xu. ICML Workshops, 2024. 电子科大
核心思想：借鉴成员推断攻击的方法，利用重建生成的中间过程完成检测
Zero-Shot Detection of AI-Generated Images. ECCV, 2024. (ZED)
Davide Cozzolino, Giovanni Poggi, Matthias Nießner, and Luisa Verdoliva
核心思想：基于coding cost的zero-shot检测，借鉴文本生成中对下一个token的预测
Leveraging Representations from Intermediate Encoder-Blocks for Synthetic Image Detection. ECCV, 2024. (RINE)
Christos Koutlis, Symeon Papadopoulos. CERTH
核心思想：使用编码器中间层的fine-grained特征，并训练一个重要性评估模块，交叉熵损失+对比损失
Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities. ECCV 2024.
Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi, Rita Cucchiara. Italy
核心思想：以往的CLIP只关注到了全局特征的提取，本文使用对比学习(InfoNCE loss)对齐全局和局部区域的相似性，添加数据增强模块模拟图像处理操作。CoDE
Evolution of Detection Performance throughout the Online Lifespan of Synthetic Images. ECCV Workshops, 2024.
Dimitrios Karageorgiou, Quentin Bammey, Valentin Por cellini, Bertrand Goupil, Denis Teyssou, and Symeon Pa padopoulos.
核心思想：随着生成图像在社交媒体中的传播，当前方法检测性能逐渐降低。并针对性提出基于检索辅助的检测方法RASID，如果相似度高就用现成的检测结果，否则就重新检测
ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models. CCS 2024.
Zeyang Sha, Yicong Tan, Mingjie Li, Michael Backes, Yang Zhang
核心思想：真实图像和生成图像对于「对抗提示」的重建程度不同。基于SSIM比较的检测
Breaking Semantic Artifacts for Generalized AI-generated Image Detection. NIPS, 2024.
Chende Zheng, Chenhao Lin, Zhengyu Zhao, Hang Wang, Xu Guo, Shuai Liu, Chao Shen
核心思想：cross-scene, patch shuffle（排除语义缺陷过拟合的影响） & patch based feature extractor + patch feature flatten. Grad-CAM
Detecting Image Attribution for Text-to-Image Diffusion Models in RGB and Beyond
Katherine Xu, Lingzhi Zhang, Jianbo Shi. NeurIPS Workshops, 2024. 宾夕法尼亚大学
核心思想：实现文生图模型生成内容检测与溯源，基于图像中高频信号、风格特征和布局
SemGIR: Semantic-Guided Image Regeneration Based Method for AI-generated Image Detection and Attribution
Xiao Yu, Kejiang Chen, Kai Zeng, Han Fang, Zijin Yang, Xiuwei Shang, Yuang Qi, Weiming Zhang, Nenghai Yu. ACM Multimedia, 2024.
核心思想：few-shot场景，基于基于语义重建的参考图像生成，训练检测/溯源分类器
Stealthdiffusion: Towards evading diffusion forensic detection through diffusion model
Z. Zhou, K. Sun, Z. Chen, H. Kuang, X. Sun, and R. Ji. ACM Multimedia, 2024. Xiamen University
核心思想：使用对抗样本逃避检测。
Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis
Sergey Sinitsa, Ohad Fried. WACV, 2024
核心思想：DIF，受Deep Image Prior图像重建启发，基于图像指纹与两类参考图像相似性.
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles. WACV, 2024.
Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash
核心思想：为抵御对抗扰动对检测结果的影响，提出频域集成学习，通过显著性分数将原始特征分为4部分，送入分类器检测
Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection. WIFS, 2024.
Vincenzo De Rosa; Fabrizio Guillaro; Giovanni Poggi; Davide Cozzolino; Luisa Verdoliva
核心思想：衡量当前CNN-based和CLIP-based的检测方法对于PGD, DI2 -FGSM, RWA, UA四种对抗扰动的鲁棒性
CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection
Sohail Ahmed Khan, Duc-Tien Dang-Nguyen. ICMR, 2024.
核心思想：基于CLIP的Prompt tuning，Adapter，Fine-tuning，Linear Probing四种方式
Frequency Masking for Universal Deepfake Detection
Chandler Timm Doloriel, Ngai-Man Cheung. ICASSP 2024. SUTD
核心思想：提出一种数据增强策略，像素域random masking/patch masking+频域masking
X-Transfer: A Transfer Learning-Based Framework for Robust GAN-Generated Fake Image Detection IJCNN, 2024.
Lei Zhang, Hao Chen, Shu Hu, Bin Zhu, Xi Wu, Jinrong Hu, Xin Wang.
核心思想：一个主网络，一个辅助网络，三路损失，加权反向传播，训练分类器。
On the Exploitation of DCT-Traces in the Generative-AI Domain
Orazio Pontorno, Luca Guarnera, and Sebastiano Battiato. ICIP, 2024.
核心思想：使用DCT变换进行检测，使用LIME进行预测结果的解释
AI-Generated Image Detection with Wasserstein Distance Compression and Dynamic Aggregation
Zihang Lyu; Jun Xiao; Cong Zhang; Kin-Man Lam. ICIP, 2024
核心思想：无监督聚类，与K-Means不同的是在Wasserstein空间
FAMSeC: A Few-shot-sample-based General AI-generated Image Detection Method. SPL, 2024.
Juncong Xu, Yang Yang, Han Fang, Honggu Liu, and Weiming Zhang. 安徽大学+新加坡国立
核心思想：伪造感知模块+语义引导的对比学习；LoRA；对比学习，小样本学习
Detecting Computer-Generated Images by Using Only Real Images
Ji Li, Kai Wang. ICMV, 2024. EI检索。
核心思想：CLIP+MLP，不同的是，生成数据是由真实数据修改得到，修改方法包括频域掩膜/patch swapping/图像融合/颜色迁移，以此增强检测结果的泛化性。
Artifact Feature Purification for Cross-domain Detection of AI-generated Images
Zheling Meng, Bo Peng, Jing Dong, Tieniu Tan, Haonan Cheng. Computer Vision and Image Understanding, 2024.
核心思想：DFT频域&可学习的正交分解空域（特征显式纯化，把图像特征分解为伪影相关特征和伪影不相关特征）+互信息估计器增大两种特征之间的距离（特征隐式纯化）。只把伪影相关特征送入分类器。
FIDAVL: Fake Image Detection and Attribution using Vision-Language Model. ICPR, 2024.
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Abdenour Hadid.
核心思想：基于BLIP2的Q-Former和Vicuna 7b
Harnessing the Power of Large Vision Language Models for Synthetic Image Detection
Mamadou Keita, Wassim Hamidouche, Hassen Bougueffa, Abdenour Hadid, Abdelmalik Taleb-Ahmed. arXiv, 2024.
核心思想：基于 ViTGPT2/BLIP 2 和 Q-Former 的分类器
Parents and Children: Distinguishing Multimodal Deepfakes from Natural Images. TOMM. 2024.
Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara.
核心思想：1-real+5-fake；解藕语义信息和风格信息，监督对比学习
Mastering Deepfake Detection: A Cutting-edge Approach to Distinguish GAN and Diffusion-model Images. TOMM. 2024
Luca Guarnera, Oliver Giudice, Sebastiano Battiato. Italy
核心思想：层级多标签分类——real/synthestic➡️GAN/DM➡️which model
Unsupervised Generative Fake Image Detector. TCSVT, 2024.
Tong Qiao, Hang Shao, Shichuang Xie, and Ran Shi.
核心思想：无监督学习
CSC-Net: Cross-Color Spatial Co-Occurrence Matrix Network for Detecting Synthesized Fake Images
Tong Qiao, Yuxing Chen, Xiaofei Zhou, Ran Shi, Hang Shao, Kunye Shen, and Xiangyang Luo. TCDS, 2024.
核心思想：使用Cross-color空间共现矩阵，利用颜色信息进行检测。
CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images
Jordan J. Bird, Ahmad Lotfi. IEEE Access, 2024.
核心思想：CNN分类，Grad-CAM对检测结果解释
Advanced Detection of AI-Generated Images Through Vision Transformers. IEEE Access, 2024.
Lamichhane, Darshan
核心思想：微调ViT
MMGANGuard: A Robust Approach for Detecting Fake Images Generated by GANs Using Multi-Model Techniques. IEEE Access, 2024.
Syed Ali Raza; Usman Habib; Muhammad Usman; Adeel Ashraf Cheema; Muhammad Sajid Khan
核心思想：纹理提取模型+预训练模型，集成学习
Enhancing Interpretability in AI-Generated Image Detection with Genetic Programming
Mingqian Lin, Lin Shang, Xiaoying Gao. ICDM Workshop, 2024.
核心思想：使用遗传编程提高检测方法的可解释性
MDTL-NET: Computer-generated image detection based on multi-scale deep texture learning
Qiang Xu, Shan Jia, Xinghao Jiang, Tanfeng Sun, Zhe Wang, and Hong Yan. Expert Systems with Applications, 2024.
核心思想：纹理特征，注意力机制；Low-rank Tensor Representation低秩张量融合
Did You Note My Palette? Unveiling Synthetic Images Through Color Statistics
Lea Uhlenbrock, Davide Cozzolino, Denise Moussa, Luisa Verdoliva, and Christian Riess. IH&MMSec, 2024.
核心思想：本文指出Perceptual loss 的使用使得两类图像在亮度上比色度上差异更大。使用颜色统计数据进行检测
Whodunit: Detection and Attribution of Synthetic Images by Leveraging Model-specific Fingerprints
Alexander Wißmann, Steffen Zeiler, Robert M. Nickel, Dorothea Kolossa. MAD Workshop, 2024.
核心思想：使用DCT、功率谱密度(Power Spectral Density, PSD)（频域）以及自相关系数（像素域）训练分类器。
Enhancing the Generalization of Synthetic Image Detection Models through the Exploration of Features in Deep Detection Models
Alireza Hajabdollah Javaheri, Hossein Motamednia, Ahmad Mahmoudi-Azanveh. MVIP, 2024.
核心思想：使用DIRE得到重建误差，将其放到CNN分类器中进行检测
Fake-GPT: Detecting Fake Image via Large Language Model. PRCV, 2024.
Yuming Fan, Dongming Yang, Jiguang Zhang, Bang Yang, and Yuexian Zou
核心思想：将图像表示成RGB数值序列作为输入，微调大语言模型Qwen，跨模态检测。
A guided-based approach for deepfake detection: RGB-depth integration via features fusion
Giorgio Leporoni, Luca Maiano, Lorenzo Papa, Irene Amerini. PRL, 2024.
核心思想：原始图像与深度图双路特征，接attention机制特征融合，后送入二分类器
Addressing Diffusion Model Based Counter-Forensic Image Manipulation for Synthetic Image Detection.
Aryan N Herur, Vaibhav Santhosh, Nishanth Shetty, Chandra Sekhar Seelamantula. India
核心思想：CLIP真假检测；若为假，DCT分类器分类manipulated / fake image
Detecting Artificial Intelligence-Generated images via deep trace representations and interactive feature fusion Image Fusion, 2024.
Qiang Xu, Xinghao Jiang, Tanfeng Sun, Hao Wang, Laijin Meng, Hong Yan.
核心思想：全局特征、low-level特征融合，注意力机制
Detecting AI Generated Images through Texture and Frequency Analysis of Patches AIVRV, 2024.
Yuming Chen, Maryam Yashtini. Basis International School Naning & Georgetown University
核心思想：PatchCraft的改进工作，纹理+频域图像块
IPD-Net: Detecting AI-Generated Images via Inter-Patch Dependencies IJACSA, 2024.
Jiahan Chen, Mengting Lo, Hailiang Liao, Tianlin Huang.
核心思想：依据块间依赖关系完成检测
A Single Simple Patch is All You Need for AI-generated Image Detection
Jiaxuan Chen, Jieteng Yao, and Li Niu. arXiv, 20240202.
核心思想：对测试图像随机裁剪，选择最简单的patch进行resize之后送到SRM Conv中，接ResNet50完成检测，方法简称：SSP
PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection
Nan Zhong, Yiran Xu, Zhenxing Qian, Xinpeng Zhang. arXiv, 20240307.
核心思想：对于真实图像和AIGC图像的平滑块和纹理块之间的对比差异不同，设计分类器进行检测。
Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection
Chuangchuang Tan, Ping Liu, RenShuai Tao, Huan Liu, Yao Zhao, Baoyuan Wu, Yunchao Wei. arXiv, 20240311. 北交
核心思想：高通滤波、低通滤波、预训练卷积层、随机初始化卷积层提取域无关特征
Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns Injection
Davide Alessandro Coccomini, Roberto Caldelli, Claudio Gennaro, Giuseppe Fiameni, Giuseppe Amato, Fabrizio Falchi. arXiv, 20240320. Italy
核心思想：仅使用真实图像，对50%真实图像在频域添加pattern作为负样本
Development of a Dual-Input Neural Model for Detecting AI-Generated Imagery
Jonathan Gallagher, William Pugsley. arXiv 20240619 University of Waterloo
核心思想：使用像素域和频域的双路网络构建分类器
Mixture of Low-rank Experts for Transferable AI-Generated Image Detection
Zihan Liu, Hanyi Wang, Yaoyu Kang, Shilin Wang. arXiv, 20240407. 上交
核心思想：基于LoRA的CLIP微调，混合专家模型
Detecting AI-Generated Images via CLIP
Alexander Moskowitz, Tyler Gaona and Jacob Peterson. arXiv, 20240412.
核心思想：直接微调CLIP
Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake. arXiv 20240528.
Di Yang, Yihao Huang, Qing Guo, Felix Juefei-Xu, Xiaojun Jia, Run Wang, Geguang Pu, and Yang Liu. 华师&新加坡南洋理工&纽约大学&武汉大学
核心思想：方法简称：TOFE，针对text-to-image模型，首先得到target image的text embedding，融合图像的high-level和low-level特征，可作为检测依据。
RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection. arXiv, 20240530.
Zhiyuan He, Pin-Yu Chen and Tsung-Yi Ho. 港中文
核心思想：training-free，基于相似度分数的检测。相较于生成图像，真实图像对细微的扰动更加鲁棒，使用DINOv2提取扰动前和扰动后图像的特征
Real-Time Deepfake Detection in the Real-World. arXiv, 20240613.
Bar Cavia, Eliahu Horwitz, Tal Reiss, Yedid Hoshen. Israel
核心思想：LaDeDa，基于局部patch特征，多个patch特征的融合
Improving Interpretability and Robustness for the Detection of AI-Generated Images
Tatiana Gaintseva, Laida Kushnareva, German Magai, Irina Piontkovskaya, Sergey Nikolenko, Marting Benning,Serguei Barannikov, Gregory Slabaugh. arXiv, 20240621. UK/Russia/Japan/France
核心思想：1）CLIP+逻辑回归；2）特征移除&注意力机制，提高鲁棒性
Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images
Santosh, Li Lin, Irene Amerini, Xin Wang, Shu Hu. arXiv, 20240908.
核心思想：在DEFAKE基础上，提出了一个双目标损失框架，将条件风险值（CVaR）和AUC损失协同作用，旨在解决训练集中困难样本和样本不均衡问题带来的挑战，并使用Sharpness-Aware Minimization,SAM锐度感知最小化提升网络泛化性。
On the Effectiveness of Dataset Alignment for Fake Image Detection. arXiv, 20241015.
Anirudh Sundara Rajan, Utkarsh Ojha, Jedidiah Schloesser, Yong Jae Lee
核心思想：将真实图像送入自编码器得到生成图像
Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models. arXiv, 20241113.
Chengdong Dong, Vijayakumar Bhagavatula, Zhenyu Zhou, Ajay Kumar. CMU/港城
核心思想：面向Sora和神经渲染模型的图像检测
Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models. arXiv, 20241128.
Chung-Ting Tsai, Ching-Yun Ko, I-Hsin Chung, Yu-Chiang Frank Wang, Pin-Yu Chen IBM/国立台湾大学
核心思想：改进RIGID，提出Contrastive Blur更好检测人脸图像；MINDER降低noise bias
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images arXiv, 20241230.
Sungik Choi, Sungwoo Park, Jaehoon Lee, Seunghyun Kim, Stanley Jungkyu Choi, Moontae Lee. LG AI Research
核心思想：training- free，原始图像与重建图像距离；低通滤波后图像与重建图像距离，类似 Aeroblade和FIRE
Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection. arXiv, 20241226.
Caiyun Xie, Dengpan Ye, Yunming Zhang, Long Tang, Yunna Lv, Jiacheng Deng, Jiawei Song
核心思想：反取证攻击
A Sanity Check for AI-generated Image Detection. ICLR, 2025.
Yan, Shilin and Li, Ouxiang and Cai, Jiayin and Hao, Yanbin and Jiang, Xiaolong and Hu, Yao and Xie, Weidi.
核心思想：AIDE，将DCT高低频局部图像块特征与CLIP全局语义特征进行concat后分类
C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection AAAI, 2025.
Chuangchuang Tan, Renshuai Tao, Huan Liu, Guanghua Gu, Baoyuan Wu, Yao Zhao, Yunchao Wei.
核心思想：通过引入类别通用提示，使用对比学习对真实图像和生成图像概念进行强化，借助LoRA微调CLIP
Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection. AAAI, 2025
Ziyou Liang, Weifeng Liu, Run Wang, Mengjie Wu, Boheng Li, Yuyang Zhang, Lina Wang, Xinyi Yang
核心思想：NTF，使用对比学习，得到真实图像的同质特征与虚假图像的特征拉远
Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective. KDD, 2025.
核心思想：SAFE，crop图像预处理，ColorJitter and RandomRotation数据增强，patch-based random masking提高对局部的注意
D^3 Scaling Up Deepfake Detection by Learning from Discrepancy. CVPR, 2025
Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu. 武汉大学
核心思想：原始图像+patch-shuffled图像两路分别送入CLIP（冻结），拼接后使用自注意力机制+FC。训练测试模式从“train-on-one and test-on-many”转变为“train-on-many and test-on-many”,
Any-Resolution AI-Generated Image Detection by Spectral Learning. CVPR, 2025
Dimitrios Karageorgiou, Symeon Papadopoulos, Ioannis Kompatsiaris, Efstratios Gavves CERTH
核心思想：SPAI，使用自监督学习训练一个频谱重建模型，基于频谱重建相似度捕捉生成图像
FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error. CVPR, 2025
Beilin Chu, Xuan Xu, Xin Wang, Yufei Zhang, Weike You, Linna Zhou. 北邮
核心思想：DIRE的衍生工作。抹除图像的中频部分，重建得到伪重建图像，与原始图像的重建图像concate进行分类
A Bias-Free Training Paradigm for More General AI-generated Image Detection. CVPR, 2025
Fabrizio Guillaro, Giada Zingarini, Ben Usman, Avneesh Sud, Davide Cozzolino, Luisa Verdoliva.
核心思想：构造无偏数据集，对齐两类图像的格式和语义特征，然后微调ViT完成检测
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model. CVPR, 2025
Zhenglin Huang, Jinwei Hu, Xiangtai Li, Yiwei He, Xingyu Zhao, Bei Peng, Baoyuan Wu, Xiaowei Huang, Guangliang Cheng
核心思想：借助大语言模型完成（real、Synthetic以及Tampered）篡改检测、定位与解释
Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images. CVPR,2025
Tai D. Nguyen, Aref Azizpour, Matthew C. Stamm
核心思想：
OpenSDI: Spotting Diffusion-Generated Images in the Open World. CVPR, 2025
Yabin Wang, Zhiwu Huang, Xiaopeng Hong 西交&英国南安普顿&哈工大
核心思想：
Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network. CVPR, 2025
Haifeng Zhang · Qinghui He · Xiuli Bi · Weisheng Li · Bo Liu · Bin Xiao
核心思想：
FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing. CVPR, 2025
Hossein Kashiani · Niloufar Alipour Talemi · Fatemeh Afghah
核心思想：
Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis. CVPR, 2025
Zexi Jia · Chuanwei Huang · Yeshuang Zhu · Hongyan Fei · Xiaoyue Duan · Yuan Zhiqiang · Ying Deng · Jiapei Zhang · Jinchao Zhang · Jie Zhou
核心思想：
Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection. CVPR, 2025
Boyong He · Yuxiang Ji · Qianwen Ye · Zhuoyue Tan · Liaoni Wu
核心思想：
Community Forensics: Using Thousands of Generators to Train Fake Image Detectors. CVPR, 2025
Jeongsoo Park · Andrew Owens
核心思想：
Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images. CVPR, 2025
Nan Zhong · Haoyu Chen · Yiran Xu · Zhenxing Qian · Xinpeng Zhang
核心思想：
Spatial-Temporal Reconstruction Error for AIGC-based Forgery Image Detection. ICASSP, 2025
Chengji Shen, Zhenjiang Liu, Kaixuan Chen, Jie Lei, Mingli Song, Zunlei Feng
核心思想：从利用单步重建误差改为利用多步重建误差
Reducing the Content Bias for AI-generated Image Detection. WACV, 2025
Seoyeon Gye, Junwon Ko, Hyounguk Shon, Minchan Kwon, Junmo Kim KAIST
核心思想：SFLD方法，多级PatchShuffle提取纹理特征，连同完整图像的高级语义特征一起送入CLIP提取特征+FC训练
Bi-LORA: A Vision-Language Approach for Synthetic Image Detection. Expert Systems, 2025
Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, David Camacho, Abdenour Hadid
核心思想：基于LoRA+BLIP2的检测
High‑resolution network‑based multi‑feature fusion for generalized forgery detection. Multimedia Systems, 2025.
Rui Liu, Sicong Zhang, Yang Xu, Weida Xu, Xinlong He
核心思想：图像空间特征+梯度图特征+多尺度高频特征融合送入分类器
Optimized frequency collaborative strategy drives AI image detection. IEEE Internet of Things Journal, 2025
Jun Li, Wentao Jiang, Liyan Shen, Yawei Ren
核心思想：纹理丰富区域&纹理贫乏区域；DCT；注意力机制
A Deepfake Image Detection Method Based on a Multi-Graph Attention Network. Electronics, 2025
Guorong Chen, Chongling Du, Yuan Yu, Hong Hu, Hongjun Duan and Huazheng Zhu
核心思想：
DeepGuard: Identification and Attribution of AI-Generated Synthetic Images Electronics, 2025.
Yasmine Namani, Ikram Reghioua, Gueltoum Bendiab, Mohamed Aymen Labiod, Stavros Shiaeles
核心思想：
FLODA: Harnessing Vision-Language Models for Deepfake Assessment. ICCE, 2025
Seunghyeon Park, Youngho Bae, Gunhui Han, Alexander W Olson
核心思想：基于Microsoft’s Florence-2视觉语言模型，先得到待测图像caption，然后连同待测图像一起送入模型直接得到检测结果。基于AntifakePrompt基准做的
HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection. arXiv, 20250110
Anant Mehta, Bryant McArthur, Nagarjuna Kolloju, Zhengzhong Tu
核心思想：module 1: CNN+CLIP图像特征融合；module 2: 边缘特征&目标检测模块等特征
Few-Shot Learner Generalizes Across AI-Generated Image Detection. arXiv, 20250115.
Shiyu Wu, Jing Liu, Jing Li, Yequan Wang
核心思想：使用小样本学习的原型网络，首先学习每个类别的原型表示，然后通过测试图像与原型表示相似度确定是否为检测图像
TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping. arXiv, 20250116.
Despina Konstantinidou, Christos Koutlis，Symeon Papadopoulos
核心思想：对高分辨率图像，挑选出v个纹理丰富区域，分别送入检测器，将预测分数的均值作为最终检测分数
LDR-Net: A Novel Framework for AI-generated Image Detection via Localized Discrepancy Representation. arXiv, 20250123.
JiaXin Chen, Miao Hu, DengYong Zhang, Yun Song, Xin Liao. 湖南大学
核心思想：
Generalizable Deepfake Detection via Effective Local-Global Feature Extraction. arXiv, 20250125.
Jiazhen Yan, Ziqiang Li, Ziwen He and Zhangjie Fu
核心思想：
Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection arXiv, 20250211
Anirudh Sundara Rajan, Yong Jae Lee University of Wisconsin-Madison
核心思想：只使用与真实图像特征无关的特征用来检测生成图像
PDA: Generalizable Detection of AI-Generated Images via Post-hoc Distribution Alignment. arXiv, 20250215.
Li Wang Wenyu Chen Zheng Li Shanqing Guo
核心思想：未知来源样本放到已知模型再生成
HRR: Hierarchical Retrospection Refinement for Generated Image Detection. arXiv, 20250225.
Peipei Yuan, Zijing Xie, Shuo Ye, Hong Chen, Yulong Wang 江汉大学
核心思想：
Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum arXiv 20250311
Shengpeng Xiao, Yuanfang Guo, Heqi Peng, Zeming Liu, Liang Yang, Yunhong Wang 北航&河北工大
核心思想：
Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Models arXiv, 20250314
Shree Singhi, Aayan Yadav, Aayush Gupta, Shariar Ebrahimi, Parisa Hassanizadeh
核心思想：
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation arXiv, 20250319
Siwei Wen, Junyan Ye, Peilin Feng, Hengrui Kang, Zichen Wen, Yize Chen, Jiang Wu, Wenjun Wu, Conghui He, Weijia Li 上海AI实验室&中山大学&北航&上交&港中文
核心思想：
LEGION: Learning to Ground and Explain for Synthetic Image Detection arXiv, 20250319
Hengrui Kang, Siwei Wen, Zichen Wen, Junyan Ye, Weijia Li, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, Conghui He 上交&北航&中山大学
核心思想：
Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models arXiv, 20250323
Jin Wang, Chenghui Lv, Xian Li, Shichao Dong, Huadong Li, Kelu Yao, Chao Li, Wenqi Shao, Ping Luo
核心思想：
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI arXiv, 20250324
Siyuan Cheng, Lingjuan Lyu, Zhenting Wang, Xiangyu Zhang, Vikash Sehwag
核心思想：
FakeReasoning: Towards Generalizable Forgery Detection and Reasoning arXiv, 20250327
Yueying Gao, Dongliang Chang, Bingyao Yu, Haotian Qin, Lei Chen, Kongming Liang, Zhanyu Ma 北邮&清华
核心思想：
FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics arXiv 20250331
Yixuan Li, Yu Tian, Yipo Huang, Wei Lu, Shiqi Wang, Weisi Lin, and Anderson Rocha 港城&中山大学
核心思想：
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning arXiv, 20250402
Zheng Yang, Ruoxin Chen, Zhiyuan Yan, Keyue Zhang, Xinghe Fu, Shuang Wu, Xiujun Shu, Taiping Yao, Junchi Yan, Shouhong Ding, Xi Li 浙大&北大&上交
核心思想：
Robust AI-Synthesized Image Detection via Multi-feature Frequency-aware Learning arXiv, 20250402
Hongfei Cai, Chi Liu, Sheng Shen, Youyang Qu, Peng Gui 澳门城市大学
核心思想：
Autonomous and Self-Adapting System for Synthetic Media Detection and Attribution arXiv, 20250404
Aref Azizpour, Tai D. Nguyen, Matthew C. Stamm Drexel University
核心思想：
PS：如有遗漏，欢迎评论区补充～
