journal article
Sep 09, 2025
Advancements in AI-Generated Content Forensics: A Systematic Literature Review
Abstract
The rapid proliferation of AI-Generated Content (AIGC), spanning text, images, video, and audio, has created a dual-edged sword of unprecedented creativity and significant societal risks, including misinformation and disinformation. This survey provides a comprehensive and structured overview of the current landscape of AIGC detection technologies. We begin by chronicling the evolution of generative models, from foundational GANs to state-of-the-art diffusion and transformer-based architectures. We then systematically review detection methodologies across all modalities, organizing them into a novel taxonomy of External Detection and Internal Detection. For each modality, we trace the technical progression from early feature-based methods to advanced deep learning, while also covering critical tasks like model attribution and tampered region localization. Furthermore, we survey the ecosystem of publicly available detection tools and practical applications. Finally, we distill the primary challenges facing the field–including generalization, robustness, interpretability, and the lack of universal benchmarks–and conclude by outlining key future directions, such as the development of holistic AI Safety Agents, dynamic evaluation standards, and AI-driven governance frameworks. This survey aims to provide researchers and practitioners with a clear, in-depth understanding of the state-of-the-art and critical frontiers in the ongoing endeavor to ensure a safe and trustworthy AIGC ecosystem.
Topics
No keywords indexed for this article. Browse by subject →
References
264
[1]
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022.
[3]
Accurate structure prediction of biomolecular interactions with AlphaFold 3
Josh Abramson, Jonas Adler, Jack Dunger et al.
Nature
10.1038/s41586-024-07487-w
[4]
Xai. 2024. Grok-2. (2024). Retrieved from https://grok2.cc/
[5]
Google. 2025. gemini-2.5-pro. (2025). Retrieved from https://deepmind.google/models/gemini/pro/
[6]
European Commission. 2024. Artificial intelligence act. (2024). Retrieved from https://artificialintelligenceact.eu/
[7]
The Council of Europe. 2024. The Framework Convention on Artificial Intelligence. (2024). Retrieved from https://www.coe.int/en/web/artificial-intelligence/the-framework-convention-on-artificial-intelligence
[8]
National Technical Committee. 2024. AI Safety Governance Framework. (2024). Retrieved from https://www.tc260.org.cn/front/postDetail.html?id=20240909102807
[10]
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Junchao Wu, Shu Yang, Runzhe Zhan et al.
Computational Linguistics
10.1162/coli_a_00549
[11]
Jingyi Deng Chenhao Lin Zhengyu Zhao Shuai Liu Qian Wang and Chao Shen. 2024. A survey of defenses against AI-generated visual media: Detection disruption and authentication. arXiv:2407.10575. Retrieved from https://arxiv.org/abs/2407.10575. (2024).
[13]
[14]
Li Lin Neeraj Gupta Yue Zhang Hainan Ren Chun-Hao Liu Feng Ding Xin Wang Xin Li Luisa Verdoliva and Shu Hu. 2024. Detecting multimedia generated by large AI models: A survey. arXiv:2402.00045. Retrieved from https://arxiv.org/abs/2402.00045. (2024).
10.36227/techrxiv.170723324.44685515/v1
[15]
Yueying Zou Peipei Li Zekun Li Huaibo Huang Xing Cui Xuannan Liu Chenghanyu Zhang and Ran He. 2025. Survey on AI-generated media detection: From non-MLLM to MLLM. arXiv:2502.05240. Retrieved from https://arxiv.org/abs/2502.05240 (2025).
[16]
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014. 2672–2680.
[17]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. 5998–6008.
[18]
Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021 (Proceedings of Machine Learning Research), Vol. 139. PMLR, 8162–8171.
[19]
OpenAI. 2023. GPT-4. (2023). Retrieved from https://openai.com/index/gpt-4/
[20]
Meta. 2025. LLaMA-4. (2025). Retrieved from https://www.llama.com/models/llama-4/
[21]
DeepSeek. 2025. DeepSeek-R1. (2025). Retrieved from https://www.deepseek.com/
[22]
Biyang Guo Xin Zhang Ziyuan Wang Minqi Jiang Jinran Nie Yuxuan Ding Jianwei Yue and Yupeng Wu. 2023. How close is ChatGPT to human experts? comparison corpus evaluation and detection. arXiv:2301.07597. Retrieved from https://arxiv.org/abs/2301.07597 (2023).
[24]
Zhenpeng Su Xing Wu Wei Zhou Guangyuan Ma and Songlin Hu. 2023. HC3 plus: A semantic-invariant human ChatGPT comparison corpus. arXiv:2309.02731. Retrieved from https://arxiv.org/abs/2309.02731. (2023).
[26]
Chujie Gao Dongping Chen Qihui Zhang Yue Huang Yao Wan and Lichao Sun. 2024. LLM-as-a-Coauthor: The challenges of detecting LLM-human mixcase. arXiv:2401.05952. Retrieved from https://arxiv.org/abs/2401.05952. (2024).
[27]
Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi Yang, Yulin Yuan, and Lidia S. Chao. 2024. DetectRL: Benchmarking LLM-generated text detection in real-world scenarios. In Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024.
[32]
Mingjian Zhu, Hanting Chen, Qiangyu Yan, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, and Yunhe Wang. 2023. GenImage: A million-scale benchmark for detecting AI-generated image. In Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023.
[37]
Shilin Yan Ouxiang Li Jiayin Cai Yanbin Hao Xiaolong Jiang Yao Hu and Weidi Xie. 2024. A sanity check for AI-generated image detection. arXiv:2406.19435. Retrieved from https://arxiv.org/abs/2406.19435. (2024).
[38]
Zhaopan Xu Pengfei Zhou Jiaxin Ai Wangbo Zhao Kai Wang Xiaojiang Peng Wenqi Shao Hongxun Yao and Kaipeng Zhang. 2025. MPBench: A comprehensive multimodal reasoning benchmark for process errors identification. arXiv:2503.12505. Retrieved from https://arxiv.org/abs/2503.12505. (2025).
10.18653/v1/2025.findings-acl.1112
[41]
Brian Dolhansky Russ Howes Ben Pflaum Nicole Baram and Cristian Canton-Ferrer. 2019. The deepfake detection challenge (DFDC) preview dataset. arXiv:1910.08854. Retrieved from https://arxiv.org/abs/1910.08854. (2019).
[43]
Haoxing Chen Yan Hong Zizheng Huang Zhuoer Xu Zhangxuan Gu Yaohui Li Jun Lan Huijia Zhu Jianfu Zhang Weiqiang Wang and Huaxiong Li. 2024. DeMamba: AI-generated video detection on million-scale genvideo benchmark. arXiv:2405.19707. Retrieved from https://arxiv.org/abs/2405.19707. (2024).
[44]
Xuan Ju, Yiming Gao, Zhaoyang Zhang, Ziyang Yuan, Xintao Wang, Ailing Zeng, Yu Xiong, Qiang Xu, and Ying Shan. 2024. MiraData: A large-scale video dataset with long durations and structured captions. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024.
[45]
Zhenliang Ni Qiangyu Yan Mouxiao Huang Tianning Yuan Yehui Tang Hailin Hu Xinghao Chen and Yunhe Wang. 2025. GenVidBench: A challenging benchmark for detecting AI-generated video. arXiv:2501.11340. Retrieved from https://arxiv.org/abs/2501.11340. (2025).
[47]
Junichi Yamagishi Xin Wang Massimiliano Todisco Md. Sahidullah Jose Patino Andreas Nautsch Xuechen Liu Kong Aik Lee Tomi Kinnunen Nicholas W. D. Evans and Héctor Delgado. 2021. ASVspoof 2021: Accelerating progress in spoofed and deepfake speech detection. arXiv:2109.00537. Retrieved from https://arxiv.org/abs/2109.00537. (2021).
10.21437/asvspoof.2021-8
[48]
Joel Frank and Lea Schönherr. 2021. WaveFake: A data set to facilitate audio deepfake detection. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021.
[49]
Xiang Li Pin-Yu Chen and Wenqi Wei. 2024. SONAR: A synthetic AI-audio detection framework and benchmark. arXiv:2410.04324. Retrieved from https://arxiv.org/abs/2410.04324. (2024).
Showing 50 of 264 references
Metrics
5
Citations
264
References
Details
- Published
- Sep 09, 2025
- Vol/Issue
- 58(3)
- Pages
- 1-36
Authors
Funding
National Natural Science Foundation of China
Award: 62272297
Shanghai Pujiang Program
Award: 24PJA056
Startup Fund for Young Faculty at SJTU
Cite This Article
Qiang Xu, Wenpeng Mu, Jianing Li, et al. (2025). Advancements in AI-Generated Content Forensics: A Systematic Literature Review. ACM Computing Surveys, 58(3), 1-36. https://doi.org/10.1145/3760526
Related
You May Also Like
A Survey on Bias and Fairness in Machine Learning
Ninareh Mehrabi, Fred Morstatter · 2021
3,466 citations