Federated Memory Aggregation for Poisoning-Resilient Multi-Agent Collaboration
PDF

Keywords

Multi-agent systems
federated aggregation
memory poisoning defense
trimmed mean
distributed collaboration
adversarial robustness

Abstract

Direct memory sharing among agents increases vulnerability to adversarial contamination. This work proposes a federated memory aggregation framework in which local agent memories are aggregated through a secure weighted update mechanism rather than direct synchronization. Each agent computes local memory updates and transmits gradient-like summaries to a central aggregation node. A trimmed-mean aggregation rule discards extreme updates likely caused by poisoning. Evaluation on a 64-agent cooperative optimization benchmark demonstrated that under a 25% poisoning rate, baseline direct-sharing systems experienced a 44.2% performance drop, while the federated aggregation framework limited degradation to 13.6%. Communication overhead increased by 9.8%, remaining within acceptable distributed system thresholds. Federated aggregation enhances robustness against poisoning while preserving collaborative performance.

PDF

References

Amirkhani, A., & Barshooi, A. H. (2022). Consensus in multi-agent systems: a review. Artificial Intelligence Review, 55(5), 3897-3935.

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.

Paredes-Saavedra, M., Vallejos, M., Huancahuire-Vega, S., Morales-García, W. C., & Geraldo-Campos, L. A. (2024). Work team effectiveness: Importance of organizational culture, work climate, leadership, creative synergy, and emotional intelligence in university employees. Administrative Sciences, 14(11), 280.

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

Hamon, R., Junklewitz, H., Garrido, J. S., & Sanchez, I. (2024). Three challenges to secure AI systems in the context of AI regulations. Ieee Access, 12, 61022-61035.

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.

Shapira, N., Wendler, C., Yen, A., Sarti, G., Pal, K., Floody, O., ... & Bau, D. (2026). Agents of chaos. arXiv preprint arXiv:2602.20021.

Hedayatnia, P., Tavakkoli, T., Amini, H., Allahbakhsh, M., & Amintoosi, H. (2025). Attack-centric by design: A program-structure taxonomy of smart contract vulnerabilities. arXiv preprint arXiv:2511.09051.

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.

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.

Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., & Raad, A. (2023). Reviewing federated learning aggregation algorithms; strategies, contributions, limitations and future perspectives. Electronics, 12(10), 2287.

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.

Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024). A survey of security strategies in federated learning: Defending models, data, and privacy. Future Internet, 16(10), 374.

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.

Al Jasem, M. S., De Clark, T., & Shrestha, A. K. (2025). Toward decentralized intelligence: A systematic literature review of blockchain-enabled AI systems. Information, 16(9), 765.

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

Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., & Raad, A. (2023). Reviewing federated learning aggregation algorithms; strategies, contributions, limitations and future perspectives. Electronics, 12(10), 2287.

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.

Ahmed, I., Syed, M. A., Maaruf, M., & Khalid, M. (2025). Distributed computing in multi-agent systems: a survey of decentralized machine learning approaches. Computing, 107(1), 2.

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.

Elsherif, K., & Mahgoub, Y. (2024). Stigmergy-Guided Self-Organizing Workload Allocation for Cost-Efficient Operation of Cloud-Native Enterprise Data Platforms. Applied Science, Engineering, and Technology Review: Innovations, Applications, and Directions, 14(6), 1-20.

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

Frattolillo, F., Brunori, D., & Iocchi, L. (2023). Scalable and cooperative deep reinforcement learning approaches for multi-UAV systems: A systematic review. Drones, 7(4), 236.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2026 Cheryl Tan, Marcus Teo, Jia Hui Ong (Author)

Downloads

Download data is not yet available.