序号	论文名称	代码链接	GitHub 星数	论文极简分类
1	Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes	GAPL	27⭐ (GitHub)	图像AIGC检测 / 生成器感知原型
2	Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning	IAPL	22⭐ (GitHub)	图像AIGC检测 / 自适应Prompt
3	PPM-CLIP: Probabilistic Prompt Modeling for Generalizable AI-Generated Image Detection	PPM-CLIP	2⭐ (GitHub)	图像AIGC检测 / CLIP概率Prompt
4	SAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learning	SAIDO-CVPR2026	5⭐ (GitHub)	图像AIGC检测 / 持续学习
5	A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images	暂未核到官方GitHub	—	图像AIGC检测 / Training-free重建式检测 (GitHub)
6	A Difference-in-Difference Approach to Detecting AI-Generated Images	DID	0⭐ (GitHub)	图像AIGC检测 / 二阶重建差分 (CVF开放获取)
7	Detecting Compressed AI-Generated Images via Phase Spectrum Robustness	作者页显示Code入口，未核到GitHub星数	—	图像AIGC检测 / 压缩鲁棒 / 相位谱
8	Cross-modal Representation Learning for Diffusion-generated Image Detection	暂未核到官方GitHub	—	扩散图像检测 / RGB+NPR跨模态
9	Diversity over Uniformity: Rethinking Representation in Generated Image Detection	DoU	11⭐ (GitHub)	图像AIGC检测 / 多样化表征
10	Enabling Supervised Learning of Generative Signatures for Generalized AI-Generated Images Detection	GenSign	3⭐ (GitHub)	图像AIGC检测 / 生成签名
11	Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images	暂未核到官方GitHub	—	图像AIGC检测 / 可疑区域推理
12	SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images	SimLBR	5⭐ (GitHub)	图像AIGC检测 / 真实图像边界建模
13	ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation	暂未核到官方GitHub	—	图像伪造检测 / 推理对齐表征
14	UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection	UniGenDet	65⭐ (GitHub)	图像生成+检测联合框架 (Hugging Face)
15	Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution	LIDA	27⭐ (GitHub)	图像生成器归因 / 溯源
16	Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection	LTD	1⭐ (GitHub)	合成图像检测 / 层一致性
17	Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification	暂未核到官方GitHub	—	AI伪造图像检测 / 伪造定位
18	Detect Any AI-Counterfeited Text Image	DanceText	15⭐ (GitHub)	AI伪造文本图像检测 / 文字图像取证
19	IncreFA: Breaking the Static Wall of Generative Model Attribution	IncreFA	5⭐ (GitHub)	生成模型归因 / 增量归因
20	CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models	暂未核到官方GitHub	—	文生图模型指纹 / 黑盒溯源
21	When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboards	暂未核到官方GitHub	—	文生图模型识别 / 来源追踪
22	Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods	STALL	16⭐ (GitHub)	AI生成视频检测 / Training-free
23	Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning	Skyra	56⭐ (GitHub)	AI生成视频检测 / 伪影推理
24	Your One-Stop Solution for AI-Generated Video Detection	AIGVDBench	32⭐ (GitHub)	AI生成视频检测Benchmark
25	CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection	CoCoVideo	8⭐ (GitHub)	AI生成视频检测Benchmark / 商业模型
26	SAGA: Source Attribution of Generative AI Videos	Project Page	非GitHub项目页	AI生成视频溯源 / 生成器归因
27	VMD-FACT: A New Video Dataset and MLLM-based Method for Detecting Realistic AI-Generated Video Misinformation	暂未核到官方GitHub	—	AI生成视频误导信息检测
28	VideoRealBench: A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videos	暂未核到官方GitHub	—	生成视频真实性评价 / 邻近方向
29	ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos	Project Page	非GitHub项目页	视频篡改定位 / 活动级伪造
30	DFD-HR: Generalizable Deepfake Detection via Hierarchical Routing Learning	暂未核到官方GitHub	—	Deepfake检测 / 层级路由
31	Unleashing Vision-Language Semantics for Deepfake Video Detection	VLAForge	16⭐ (GitHub)	Deepfake视频检测 / VLM语义
32	Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection	暂未核到官方GitHub	—	Deepfake检测 / Token级伪造净化 (CVF开放获取)
33	X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection	Project Page	非GitHub项目页	音视频Deepfake检测 / 交叉注意力 (Homepage)
34	Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection	暂未核到官方GitHub	—	音视频Deepfake检测 / 自监督表征
35	FVBench: Benchmarking Deepfake Video Detection Capability of Large Multimodal Models	FVBench	0⭐ (GitHub)	Deepfake视频检测Benchmark / LMM评测
36	AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs	暂未核到官方GitHub	—	音视频伪造检测Benchmark
37	Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection	Project Page	非GitHub项目页	多模态社交媒体Deepfake Benchmark
38	TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection	暂未核到官方GitHub	—	可解释Deepfake检测Benchmark
39	Pixels Don’t Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision	DeepfakeJudge	10⭐ (GitHub)	Deepfake检测 / MLLM-as-Judge
40	Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection	暂未核到官方GitHub	—	人脸伪造检测 / 多智能体数据构造 (arXiv)
41	DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization	暂未核到官方GitHub	—	人脸伪造检测 / 伪影定位 (xiangyuzhu-open.github.io)
42	Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization	暂未核到官方GitHub	—	Deepfake定位 / 音视频不一致
43	A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World	暂未核到官方GitHub	—	人脸伪造检测协议 / 真实部署
44	DeepfakeImpact: A Two-Stage Benchmark with Real-World Impact in Deepfake Detection	暂未核到官方GitHub；检索到Stage1相关仓库线索但未确认完整官方项目	—	Deepfake检测Benchmark / 现实影响评估 (CVF开放获取)
45	Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection	Fairness-Optimization	3⭐ (GitHub)	Deepfake检测 / 公平性优化
46	Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection	TSRL	2⭐ (GitHub)	Deepfake检测 / 强化学习课程
47	All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark	LIDMark	13⭐ (GitHub)	Deepfake检测+定位+溯源 / 主动水印
48	PECCVAI: Overcoming the Brittleness of AI Image Watermarking Under Visual Paraphrasing Attacks	官方短链代码入口；未核到GitHub星数	—	AI图像水印 / 鲁棒性
49	Rel-Zero: A Zero-Shot Framework for Text-Image Relevance-Based Watermark Against Image Edits	暂未核到官方GitHub	—	图像水印 / AI编辑鲁棒
50	NOWA: Null-space Optical Watermark for Invisible Capture Fingerprinting and Tamper Localization	暂未核到官方GitHub	—	光学水印 / 图像真实性与篡改定位
51	MaxMark: Versatile and Practical Diffusion-native Image Watermarking	MaxMark	4⭐ (GitHub)	扩散图像水印 / 主动溯源