Game-Theoretic Analysis of Memory Poisoning Dynamics in Competitive Multi-Agent Collaboration
DOI:
https://doi.org/10.66238/fsrma52Keywords:
Multi-agent systems, memory poisoning, game theory, Nash equilibrium, adversarial dynamics, collaborative securityAbstract
Memory poisoning in multi-agent collaborative environments can be modeled as a strategic adversarial interaction between malicious and cooperative agents. This study formulates poisoning propagation as a repeated stochastic game, where agents choose memory update strategies under uncertainty. A Nash equilibrium analysis is conducted to characterize stable contamination states. Theoretical derivation identifies a critical poisoning incentive coefficient beyond which malicious memory injection becomes evolutionarily stable. Simulations were performed on networks of 100 agents across 1,000 interaction rounds. When adversarial utility exceeded 0.38 relative to cooperative reward, contamination equilibrium emerged in 72.5% of trials. Introducing adaptive penalty reinforcement reduced equilibrium contamination probability to 19.4%. The framework provides formal insight into strategic stability conditions of poisoning behavior and informs incentive-based mitigation design.
References
Standen, M., Kim, J., & Szabo, C. (2025). Adversarial machine learning attacks and defences in multi-agent reinforcement learning. ACM Computing Surveys, 57(5), 1-35.
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.
Liu, H., Xu, D., Ma, Q., Xu, S., & Qiu, D. (2026). Memory Poisoning Propagation and Repair Mechanism in Multi-Agent Collaborative Environments.
Heuthe, V. L., Panizon, E., Gu, H., & Bechinger, C. (2024). Counterfactual rewards promote collective transport using individually controlled swarm microrobots. Science Robotics, 9(97), eado5888.
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.
Chhabra, A., Datta, S., Nahin, S. K., & Mohapatra, P. (2025). Agentic ai security: Threats, defenses, evaluation, and open challenges. arXiv preprint arXiv:2510.23883.
Williamson, S. M., & Prybutok, V. (2024). The era of artificial intelligence deception: unraveling the complexities of false realities and emerging threats of misinformation. Information, 15(6), 299.
Qiu, Y. (2024). Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling. arXiv preprint arXiv:2407.05933.
Morones-Ramírez, J. R. (2025). Biocircuitry and Living Programmable Materials: The Next Frontier in Synthetic Living Systems. ACS Materials Letters, 7(8), 2910-2935.
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.
Weil, J. F. (2025). Deep Reinforcement Learning in Communication Systems–Addressing Partial Observability in Decentralized Multi-Agent Systems with Learned Communication (Doctoral dissertation).
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.
Nicholaus, I. T., & Kang, D. K. (2022). Robust experience replay sampling for multi-agent reinforcement learning. Pattern Recognition Letters, 155, 135-142.
Clempner, J. B. (2025). Learning Deceptive Tactics for Defense and Attack in Bayesian–Markov Stackelberg Security Games. Mathematical and Computational Applications, 30(2), 29.
Li, T., Liu, S., Hong, E., & Xia, J. (2025). Human Resource Optimization in the Hospitality Industry Big Data Forecasting and Cross-Cultural Engagement.
Holla, H., Polepalli, S. R., & Sasikumar, A. A. (2025). Adversarial threats to cloud IDS: robust defense with adversarial training and feature selection. IEEE Access.
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.
Ferdous, J., Islam, R., Mahboubi, A., & Islam, M. Z. (2023). A review of state-of-the-art malware attack trends and defense mechanisms. IEEe Access, 11, 121118-121141.
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.
Oroojlooy, A., & Hajinezhad, D. (2023). A review of cooperative multi-agent deep reinforcement learning. Applied Intelligence, 53(11), 13677-13722.
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.
Beisecker, S., & Schlereth, C. (2024). Offering prosocial incentives on‐top: Do they sweeten the deal or poison the well?. Psychology & Marketing, 41(3), 628-648.
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.
Ahmad, N. R. (2025). Blockchain beyond buzzwords: Evaluating its practical application in Pakistan’s supply chain systems. Quarterly Review Journal of Social Sciences. https://doi.org/10.63878/qrjs253
Safdar, M. R. (2025). Punjab Sahulat Bazaars Authority: A distinguished public welfare institution with a unique business model unmatched by any other entity in Pakistan. Contemporary Journal of Social Sciences and Research, 3(3). https://doi.org/10.63878/cjssr.v3i3.1311
Ahmad, N. R. (2025). Monetary policy, inflation and unemployment: The interactions and their economic impacts in Pakistan. Pakistan Journal of Economics and Public Policy, 5(1), 66–81.
Ahmad, N. R. (2025). Leadership ethics in practice: Employees’ experiences of integrity and hypocrisy in public-sector organizations in Pakistan. Journal of Applied Leadership and Transparency. https://doi.org/10.63878/jalt874
Toor, M. J., Shabbir, S., Rauf, A., Nisar, A., Safdar, S., & Zaib-Un-Nisa. (n.d.). The role of structured-communication-technique in developing pragmatic language capability among ASD-children. https://doi.org/10.63878/cjssr.v3i2.785
Toor, M. J., Mehmood, H., Yasmeen, A., Honey, Q., Waseem, M., & Wasif, M. (n.d.). Exploring the effect of verbal encouraging phrases (VEP) on Chinese language learners’ academic achievement at university level.
Toor, M. J., Arafat, M., Ayoub, M., Ali, M., & Alessi Longa, F. E. (n.d.). From coherent self to fragmented persona: Digital identity fragmentation and academic self-concept among Generation Z, with comparative insights from Generation Alpha. https://doi.org/10.63878/cjssr.v4i2.2318
Katsitadze, N., Kharadze, N., & Pirtskhalaishvili, D. (2025). The impact of social media on students’ effective time management. Baltic Journal of Economic Studies, 11(1), 200–210. https://doi.org/10.30525/2256-0742/2025-11-1-200-210
Toor, M. J., Zafar, S., Omer, F., Sarwar, M., & Hussain, A. K. (n.d.). Teachers’ perspectives on effectiveness of translanguaging in enhancing English language learning at secondary school level.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jeroen van der Meer, Pieter de Vries, Thomas van Dijk
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/
