SSRScientific and Social Research2661-43322981-9946Bio-Byword Scientific Publishing Pty. Ltd.10.26689/ssr.v7i10.12740ArticleOn Leveraging Multi-Agent Models in Countermeasures for Deepfake Detection and Mitigation: A Comparative Analysis of Social Media Platform Strategieshttps://artdesignp.com/journal/SSR/7/10/10.26689/ssr.v7i10.12740LiuYuanyuan,ZhangYu,SunJicheng20257102025-10-29The proliferation of deepfake content on social media in recent years has posed significant threats to both individual and societal security. Consequently, devising effective countermeasures to curb the spread of deepfake information has become a critical challenge for social media platforms worldwide. This study aims to explore the propagation dynamics of deepfake information and evaluate the efficacy of various countermeasures by constructing a multi-agent model that integrates the SIR epidemiological model with the BA scale-free network theory. The research focuses on three distinct social media platforms in China—Douyin, Weibo, and Bilibili—as case studies. Through a series of simulation experiments, we compare the propagation patterns of deepfake content and analyze the performance differences of various countermeasures. The results indicate that, in terms of preventing the dissemination of deepfake information, the “preemptive defense” mechanism (exemplified by Douyin) proves to be the most effective in limiting the spread of deepfakes and ensuring timely counteractions. In contrast, the “post-verification” framework (exemplified by Weibo) is particularly effective in enhancing immunity against deepfake content. However, countermeasures based on self-media strategies that emphasize “emotion, viewpoints, and stances” (exemplified by Bilibili) demonstrate higher infection rates, weaker immunity, and longer response delays. The findings of this study offer valuable insights for developing more efficient and adaptive information governance strategies.

Wu J, Gan W, Chen Z, et al., 2023, AI-Generated Content (AIGC): A Survey. arXiv, accessed on October 2, 2025. https://arxiv.org/abs/2304.06632

Tsinghua University Institute for Artificial Intelligence, 2022, Top 10 Trends in Deep Synthesis. Retrieved on October 2, 2025, https://www.digitalelite.cn/h-nd-3039.html

Cai S, 2020, The Technical Logic and Legal Changes of Deepfake. Political and Legal Review, 2020(3): 131–140.

Dash B, Sharma P, 2023, Are ChatGPT and Deepfake Algorithms Endangering the Cybersecurity Industry? A Review. International Journal of Engineering and Applied Sciences, 10(1): 4–5.

Chen Y, Wang W, 2023, From “Immediate Implementation” to “Gradual Improvement”: Constructing the Governance System of Generative AI. E-Government, 2023: 15–27.

El-Sayed Atlam M, Malik Almaliki G, Ghada Elmarhomy, et al., 2025, SLM-DFS: A Systematic Literature Map of Deepfake Spread on Social Media. Alexandria Engineering Journal, 2025(111): 446–455.

Wang G, Zhang Z, 2024, Characteristics, Risks, and Countermeasures of Deepfake Technology. New Media and Network, 1(2): 40–51.

Zhang X, Wang R, Ma Y, 2024, Challenges, Opportunities, and Strategies in Fake Information Governance Under the AIGC Context. Information Science, 1–23, accessed on October 2, 2025, https://link.cnki.net/urlid/22.1264.G2.20241111.1002.024

Zhao L, Wang J, Cheng J, et al., 2012, Rumor Spreading Model with Consideration of Forgetting and Remembering Mechanisms in Social Networks. Physica A: Statistical Mechanics and its Applications, 391(7): 2444–2453.

Sadiq S, Aljrees T, Ullah S, 2023, Deepfake Detection on Social Media: Leveraging Deep Learning and FastText Embeddings for Identifying Machine-Generated Tweets. IEEE Access, 2023(11): 95008–95021.

Khan AA, Chen YL, Hajjej F, et al., 2024, Digital Forensics for the Socio-Cyber World (DF-SCW): A Novel Framework for Deepfake Multimedia Investigation on Social Media Platforms. Egyptian Informatics Journal, 27(1): 1–12.

Mao H, 2013, Core Elements of the Cross-Strait Dialogue System, thesis, Fujian Normal University.

Jiang S, Han Z, 2011, Agent-Based Modeling Methods in Complex Systems Research. Journal of the University of Shanghai for Science and Technology, 33(2): 124–129.

Pan J, Shen H, Chen Z, 2018, A Model of Group Event Microblog Propagation Based on Agent and K-Core Decomposition. Information Science, 36(2): 125–131.

Sun R, Luo W, 2014, Rumor Spreading Model in Scale-Free Networks with Non-Uniform Propagation Rates. Complex Systems and Complexity Science, 11(3): 6–11.

Liu C, Chen M, 2023, User Perception and Interaction Behaviors of False Information Based on Cue Utility Theory: Focused on Deepfake Information. Journal of Information Science, 42(10): 96–104.

Vosoughi S, Roy D, Aral S, 2018, The Spread of True and False News Online. Science, 359(6380): 1146–1151.

Zhao L, Wang J, Chen Y, et al., 2012, SIHR Rumor Spreading Model in Social Networks. Physica A: Statistical Mechanics and its Applications, 391(7): 2444–2453.

Friggeri A, Adamic L, Eckles D, et al., 2014, Rumor Cascades. Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media, 101–110.

Granell C, Gomez S, Arenas A, 2013, Dynamical Interplay Between Awareness and Epidemic Spreading in Multiplex Networks. Physical Review Letters, 111(12): 128701.