Generative AI and Digital Ecosystem resilience: A Proactive Lifecycle-Based Survey
Abstract
The proliferation of misinformation, accelerated by Generative AI (GenAI) is rendering
traditional reactive detection methods ineffective. This survey suggests that the effort for the misinformation detection paradigm should shift toward the proactive detection of emerging inauthentic narratives instead. In this survey, we adopt a unified, lifecycle-based taxonomy to combine socio-technical lifecycle models of misinformation with advanced computational methodologies for emerging inauthentic narrative detection. By structuring the analysis around the C5 Interaction Model (Context, Causes, Content, Cycle of Amplification, Consequences), we integrate different research streams from machine learning and social science. To differentiate how spread patterns of misinformation from organic news, this paper surveys state-of-the-art techniques for modeling the creation, seeding, and propagation of fresh narratives, including the analysis of Coordinated Inauthentic Behavior (CIB), epidemiological modeling, and Hawkes process. This survey also provides a systematic review of proactive detection methods for misinformation at different stages in the C5 interaction model—specifically, anomaly detection in high-dimensional embedding spaces, unsupervised coordination detection on multi-layer graphs, and agentic AI systems. Finally, this survey addresses challenges posed by GenAI, including the difficulty of tracking rapidly changing threats and multilevel distributional drift, and it outlines a future research agenda focused on detecting anomalous clusters and
building anticipatory and resilient systems. This survey provides a comprehensive, lifecycle-based review of methods for the proactive detection of emerging misinformation for more resilient information ecosystems.
traditional reactive detection methods ineffective. This survey suggests that the effort for the misinformation detection paradigm should shift toward the proactive detection of emerging inauthentic narratives instead. In this survey, we adopt a unified, lifecycle-based taxonomy to combine socio-technical lifecycle models of misinformation with advanced computational methodologies for emerging inauthentic narrative detection. By structuring the analysis around the C5 Interaction Model (Context, Causes, Content, Cycle of Amplification, Consequences), we integrate different research streams from machine learning and social science. To differentiate how spread patterns of misinformation from organic news, this paper surveys state-of-the-art techniques for modeling the creation, seeding, and propagation of fresh narratives, including the analysis of Coordinated Inauthentic Behavior (CIB), epidemiological modeling, and Hawkes process. This survey also provides a systematic review of proactive detection methods for misinformation at different stages in the C5 interaction model—specifically, anomaly detection in high-dimensional embedding spaces, unsupervised coordination detection on multi-layer graphs, and agentic AI systems. Finally, this survey addresses challenges posed by GenAI, including the difficulty of tracking rapidly changing threats and multilevel distributional drift, and it outlines a future research agenda focused on detecting anomalous clusters and
building anticipatory and resilient systems. This survey provides a comprehensive, lifecycle-based review of methods for the proactive detection of emerging misinformation for more resilient information ecosystems.
