Consensus-Guided Redundant Memory Isolation for Poisoning Mitigation in Collaborative Agent Frameworks
DOI:
https://doi.org/10.66525/ijictt73Keywords:
Multi-agent collaboration, memory isolation, consensus mechanisms, adversarial resilience, distributed systems security, poisoning mitigationAbstract
Memory poisoning can destabilize collaborative decision-making when agents rely on shared state synchronization. This study introduces a consensus-guided redundant memory isolation mechanism to prevent cross-agent contamination. Agents maintain parallel memory replicas and compute consensus confidence scores using weighted majority voting across trusted peers. Memory segments with confidence below 0.65 are temporarily isolated and revalidated before reintegration. Evaluation was conducted on a distributed task allocation benchmark with 60 agents under varying poisoning rates (5%–25%). The isolation mechanism reduced collective performance degradation by 42.1% and limited contamination spread to fewer than 18% of agents, compared with 61% under standard synchronization. Communication overhead increased by 12.7%, remaining within acceptable system bounds. The approach strengthens robustness while maintaining scalability in collaborative environments.
Downloads
References
Hasan, R. (2025). A Systematic Review Of Human-AI Collaboration In It Support Services: Enhancing User Experience And Workflow Automation. American Journal of Interdisciplinary Studies, 6(3), 01-37.
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.
Enßlin, T. A., Kainz, V., & Boehm, C. (2023). Simulating reputation dynamics and their manipulation: An agent based model framework. Computational Communication Research, 5(1), 1.
Qiu, Y. (2024). Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling. arXiv preprint arXiv:2407.05933.
Youvan, D. C. (2025). Pure Information from Quantum Randomness: QRNGs as Interfaces Between Substrate, Qubits, and the It-From-Bit Cosmos.
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.
Liu, H., Xu, D., Ma, Q., Xu, S., & Qiu, D. (2026). Memory Poisoning Propagation and Repair Mechanism in Multi-Agent Collaborative Environments.
Ponniah, J., & Dantsker, O. D. (2022). Strategies for scaleable communication and coordination in multi-agent (uav) systems. Aerospace, 9(9), 488.
Tran, K. T., Dao, D., Nguyen, M. D., Pham, Q. V., O'Sullivan, B., & Nguyen, H. D. (2025). Multi-agent collaboration mechanisms: A survey of llms. arXiv preprint arXiv:2501.06322.
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.
Alamsabi, M., Tchuindjang, M., & Brohi, S. (2026). Embedding-Based Detection of Indirect Prompt Injection Attacks in Large Language Models Using Semantic Context Analysis. Algorithms, 19(1), 92.
Li, T., Liu, S., Hong, E., & Xia, J. (2025). Human Resource Optimization in the Hospitality Industry Big Data Forecasting and Cross-Cultural Engagement.
Małuszyński, M. J., Pawluśkiewicz, B., Gnatowski, T., Małuszyńska, I., Wołejko, E., Wydro, U., ... & Dąbrowski, P. (2026). The Effect of Petroleum-Derived Compounds in Soil on Microbiological Activity and the Physiological State of Plants. Applied Sciences, 16(4), 2076.
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.
Amirkhani, A., & Barshooi, A. H. (2022). Consensus in multi-agent systems: a review. Artificial Intelligence Review, 55(5), 3897-3935.
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.
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.
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.
Sunil, B. D., Sinha, I., Maheshwari, P., Todmal, S., Mallik, S., & Mishra, S. (2026). Memory Poisoning Attack and Defense on Memory Based LLM-Agents. arXiv preprint arXiv:2601.05504.
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.
Amirkhani, A., & Barshooi, A. H. (2022). Consensus in multi-agent systems: a review. Artificial Intelligence Review, 55(5), 3897-3935.
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.
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
Issue
Section
License
Copyright (c) 2026 Michael J. Smith, David R. Thompson, Emily K. Brown (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the International Journal of Information and Communication Technology Trends (IJICTT) are distributed under a Creative Commons license. This allows readers to freely access, share, and adapt the content for non-commercial purposes, provided proper attribution is given to the original authors. Authors retain copyright of their work.
