Dynamic Trust Decay Modeling for Containment of Memory Poisoning in Collaborative Agent Networks

Authors

  • Oliver Bennett Department of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PL, United Kingdom Author
  • Daniel Hughes Department of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PL, United Kingdom Author
  • Emily Carter Department of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PL, United Kingdom Author

DOI:

https://doi.org/10.66525/ijictt71

Keywords:

Multi-agent systems, trust modeling, memory poisoning containment, credibility decay, collaborative networks, resilience mechanisms

Abstract

 Persistent poisoning may exploit static trust assumptions among agents. This study introduces a dynamic trust decay model in which agent credibility scores decrease proportionally to detected inconsistency in memory contributions. Trust scores are updated using a nonlinear decay function based on deviation magnitude and frequency. Agents with trust below a predefined threshold are temporarily restricted from contributing shared memory. Simulations were conducted on 120-agent coordination tasks with varying poisoning intensities. The trust decay mechanism reduced cross-agent contamination spread by 57.2% and improved overall task success rate from 62.8% to 84.5% under a 20% poisoning scenario. System stability was restored within 18 update cycles compared to 41 cycles in static-trust settings. Dynamic trust modeling effectively limits poisoning persistence and accelerates recovery in collaborative environments.

Downloads

Download data is not yet available.

References

Bai, W., Wu, Q., Wu, K., & Lu, K. (2024). Exploring the Influence of Prompts in LLMs for Security-Related Tasks. In Workshop on Artificial Intelligence System with Confidential Computing (AISCC 2024)(San Diego, CA). USA. https://dx. doi. org/10.14722/aiscc.

Batista, A. D. S., & Dos Santos, A. L. (2024). A survey on resilience in information sharing on networks: Taxonomy and applied techniques. ACM Computing Surveys, 56(12), 1-36.

Liu, H., Xu, D., Ma, Q., Xu, S., & Qiu, D. (2026). Memory Poisoning Propagation and Repair Mechanism in Multi-Agent Collaborative Environments.

Agarwal, D., Shahid, F., & Vashistha, A. (2024). Conversational agents to facilitate deliberation on harmful content in whatsapp groups. Proceedings of the ACM on human-computer interaction, 8(CSCW2), 1-32.

Krishnan, N. (2025). Advancing multi-agent systems through model context protocol: Architecture, implementation, and applications. arXiv preprint arXiv:2504.21030.

Du, Y. (2025). Research on Deep Learning Models for Forecasting Cross-Border Trade Demand Driven by Multi-Source Time-Series Data. Journal of Science, Innovation & Social Impact, 1(2), 63-70.

Chen, H., Li, J., Ma, X., & Mao, Y. (2025, June). Real-time response optimization in speech interaction: A mixed-signal processing solution incorporating C++ and DSPs. In 2025 7th International Conference on Artificial Intelligence Technologies and Applications (ICAITA) (pp. 110-114). IEEE.

Zambare, P., Thanikella, V. N., & Liu, Y. (2025). Securing agentic ai: Threat modeling and risk analysis for network monitoring agentic ai system. arXiv preprint arXiv:2508.10043.

Rahman, M. A., Francia, G., Shahriar, H., Cuzzocrea, A., Mohamed, A., Khan, M. U., & Ahamed, S. I. (2025, December). A Survey of Large Language Models (LLMs) for Cybersecurity: Opportunities and Directions. In 2025 IEEE International Conference on Big Data (BigData) (pp. 4333-4342). IEEE.

Li, T., Liu, S., Hong, E., & Xia, J. (2025). Human Resource Optimization in the Hospitality Industry Big Data Forecasting and Cross-Cultural Engagement.

Maragheh, R. Y., & Deldjoo, Y. (2025). The future is agentic: Definitions, perspectives, and open challenges of multi-agent recommender systems. arXiv preprint arXiv:2507.02097.

Qiu, D., Xu, D., & Yue, L. (2025, December). Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization. In 2025 7th International Conference on Frontier Technologies of Information and Computer (ICFTIC) (pp. 1337-1342). IEEE.

Habibullah, S. M., & Dhanekula, A. (2023). Blockchain-Orchestrated Cyber-Physical Supply Chain Networks with Byzantine Fault Tolerance For Manufacturing Robustness. Journal of Sustainable Development and Policy, 2(03), 34-72.

Gu, X., Yang, J., Tian, X., & Liu, M. (2025). Research on the Construction of a Human-Machine Collaborative Anti-Money Laundering System and Its Efficiency and Accuracy Enhancement in Suspicious Transaction Identification.

Batista, A. D. S., & Dos Santos, A. L. (2024). A survey on resilience in information sharing on networks: Taxonomy and applied techniques. ACM Computing Surveys, 56(12), 1-36.

Yang, Y., Leuze, C., Hargreaves, B., Daniel, B., & Baik, F. (2025). EasyREG: Easy Depth-Based Markerless Registration and Tracking using Augmented Reality Device for Surgical Guidance. arXiv preprint arXiv:2504.09498.

de Witt, C. S. (2025). Open challenges in multi-agent security: Towards secure systems of interacting ai agents. arXiv preprint arXiv:2505.02077.

Liu, S., Feng, H., & Liu, X. (2025). A Study on the Mechanism of Generative Design Tools' Impact on Visual Language Reconstruction: An Interactive Analysis of Semantic Mapping and User Cognition. Authorea Preprints.

Bonfanti, R. C., Ruggieri, S., & Schimmenti, A. (2024). Psychological trust dynamics in climate change adaptation decision-making processes: a literature review. Sustainability, 16(10), 3984.

Ma, Q., Yue, L., Xu, S., Shi, Y., & Liu, H. (2026). Web Agent Agentic Reinforcement Learning Decision Model Under Multi-Cost and Failure Risk Constraints.

Sameer, M. M. (2025). A Context-Aware Hybrid Trust Management Model for the Internet of Vehicles.

Qiu, Y. (2024). Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling. arXiv preprint arXiv:2407.05933.

Lygizou, Z., & Kalles, D. (2025). A biologically inspired trust model for open multi-agent systems that is resilient to rapid performance fluctuations. Applied Sciences, 15(11), 6125.

Ahmad, N. R. (2025). Exploring the role of digital technologies in enhancing supply chain efficiency: A case study of e-commerce companies. Indus Journal of Social Sciences, 3(1), 226–237. https://doi.org/10.59075/ijss.v3i1.618

Downloads

Published

2026-03-15