Systematic Review of Reliability and Trustworthiness on Multi-Agent Architectures
Resumo
Os Sistemas Multiagente (SMAs) emergem como uma abordagem promissora para a construção de estratégias de defesa adaptativas e distribuídas. Este artigo apresenta uma Revisão Sistemática da Literatura (RSL) com o objetivo de identificar aspectos arquiteturais essenciais de confiabilidade em SMAs. Os resultados foram organizados em torno das seguintes dimensões: ataques e vulnerabilidades em SMAs, soluções propostas para mitigação, métodos para identificar anomalias comportamentais e características arquiteturais de sistemas confiáveis e dignos de confiança. Por fim, resumindo um conjunto de abordagens que podem ser aplicadas em MAS para atender a este requisito, e destacando-se uma delas para futuras implementações nesse contexto.
Referências
Ahmed, M., Ansar, K., Muckley, C. B., Khan, A., Anjum, A., and Talha, M. (2021). A semantic rule based digital fraud detection. PeerJ Computer Science, 7:e649. Modelo ontológico para detecção e alerta de fraudes digitais financeiras.
Alruqi, M., Hsairi, L., and Eshmawi, A. (2021). Secure mobile agents for patient status telemonitoring using blockchain. page 224–228.
Baradarannia, M., Hashemzadeh, F., and Kumbasar, T. (2025). Fixed-time surrounding control of multi-agent systems underdenial-of-service attacks. JOURNAL OF THE FRANKLIN INSTITUTE, 362.
Barambones, J., Richoux, F., Imbert, R., and Inoue, K. (2021). Resilient Team Formation with Stabilisability of Agent Networks for Task Allocation. ACM Trans. Auton. Adapt. Syst., 15.
Choi, I.-S., Hong, J., and Kim, T.-W. (2020). Multi-Agent Based Cyber Attack Detection and Mitigation for DistributionAutomation System. IEEE ACCESS, 8:183495–183504.
Damle, S., Triastcyn, A., Faltings, B., and Gujar, S. (2022). Differentially Private Multi-Agent Constraint Optimization. page 422–429.
de la Hoz, E., Gimenez-Guzman, J. M., Marsa-Maestre, I., Cruz-Piris, L., and Orden, D. (2017). A Distributed, Multi-Agent Approach to Reactive Network Resilience. page 1044–1053.
Deng, F., Xu, C., Guan, Z.-H., and Chen, G. (2024). Dynamic event-triggered quantized secure output consensus ofheterogeneous multi-agent systems under DoS attacks. CHAOS, 34.
Esmaeili, A., Ghorrati, Z., and Matson, E. T. (2024). Holonic Learning: A Flexible Agent-based Distributed Machine Learning Framework. page 525–533.
Felizardo, K. et al. (2017). Revisão sistemática da literatura em engenharia de software: teoria e prática. Elsevier Brasil.
Gao, R. and Yang, G.-H. (2024). Trust-Based Distributed Secure State Estimation Against Malicious Agentsvia Two-Hop Communication. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 69:1006–1013.
Hajar, M. S., Kalutarage, H. K., and Al-Kadri, M. (2023). 3R: A reliable multi agent reinforcement learning based routing protocolfor wireless medical sensor networks. COMPUTER NETWORKS, 237.
Hao, Q., Luo, M., Cheng, J., and Shi, K. (2025). Distributed fault-tolerant consensus for two-time-scale multiagentsystems against multiple faults and random attacks via a generalizedtwo-step transmission mechanism. JOURNAL OF THE FRANKLIN INSTITUTE, 362.
He, W., Xu, W., Ge, X., Han, Q.-L., Du, W., and Qian, F. (2022). Secure Control of Multiagent Systems Against Malicious Attacks: A BriefSurvey. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 18:3595–3608.
Huang, X. and Dong, J. (2020). Reliable Leader-to-Follower Formation Control of Multiagent SystemsUnder Communication Quantization and Attacks. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 50:89–99.
Jain, G. and Solomon Jebaraj, N. R. (2023). Taxonomy of Multi-Agent Systems Attacks and their Defense Tactics in Certifying Security of Cyber Physical Systems. pages 648–652.
Kott, A. (2023). Autonomous Intelligent Cyber Defense Agent (AICA): A Comprehensive Guide, volume 87 of Advances in Information Security. Springer.
Li, Y., Fang, H., and Chen, J. (2020). Anomaly Detection and Identification for Multiagent Systems Subjected toPhysical Faults and Cyberattacks. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 67:9724–9733.
Lin, B.-Y., Dziubałtowska, D., Macek, P., Penzkofer, A., and Müller, S. (2023). Tangle-Sim: An Agent-based, Modular Simulator for DAG-based Distributed Ledger Technologies. pages 1–5.
Lin, H., Dong, J., and Park, J. H. (2025). An Artificial-Delay-Based Looped Functional for Dynamic Event-Triggered Fault-Tolerant Control of T-S Fuzzy Multi-Agent Systems. IEEE Transactions on Automation Science and Engineering, 22:6050–6060.
Lu, C., Zhu, J., and Ouyang, L. (2024). Mission Reliability and Optimization in Multi-Agent Systems Using Hyperledger Fabric Platform. pages 1–6.
Lygizou, Z. and Kalles, D. (2025). A Biologically Inspired Trust Model for Open Multi-Agent Systems That IsResilient to Rapid Performance Fluctuations. APPLIED SCIENCES-BASEL, 15.
Mao, Y., Kang, Y., Li, P., Zhang, N., Xu, W., and Zhang, C. (2025). IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. page 2654–2656.
Marques, R. S., Epiphaniou, G., Al-Khateeb, H., Maple, C., Hammoudeh, M., De Castro, P. A. L., Dehghantanha, A., and Choo, K. K. R. (2021). A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks. ACM Trans. Internet Technol., 21.
Masters, C., Vellanki, A., Shangguan, J., Kultys, B., Gilmore, J., Moore, A., and Albrecht, S. (2025). Orchestrating Human-AI Teams: The Manager Agent as aUnifying Research Challenge. page 91–107.
Phiri, C. C. (2025). Creating Characteristically Auditable Agentic AI Systems. page 1–14.
Pretila, H., Campbell, B., and Szabo, C. (2024). Contested Communication in C2 Multi-agent Simulations. page 25–29.
Toumi, H., Marzak, B., Khazri, Y., Talea, A., Eddaoui, A., and Talea, M. (2017). Mobiles Agents and Virtual Firewall to Secure the Shared Network for Virtual Machines in IaaS cloud.
Wen, X., Wen, J., Xiao, M., Kang, J., Zhang, T., Li, X., Chen, C., and Niyato, D. (2026). Defending Against Network Attacks for Secure AI Agent Migration in Vehicular Metaverses. IEEE Internet of Things Journal, 13:4153–4166.
Xue, W., Qiu, W., An, B., Rabinovich, Z., Obraztsova, S., and Yeo, C. K. (2022). Misspoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning. page 1418–1426.
Yuan, T., Chung, H.-M., and Fu, X. (2024). PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications. IEEE Network, 38:196–203.
Zhang, S., Ma, Y., Chen, J., Li, S., Yi, X., and Li, H. (2025a). Towards Aligning Personalized AI Agents with Users’ Privacy Preference. page 33–42.
Zhang, X., Dong, X., Wang, Y., Zhang, D., and Cao, F. (2025b). A Survey of Multi-AI Agent Collaboration: Theories, Technologies and Applications. page 1875–1881.
Zhang, Z., Yao, Y., Zhang, A., Tang, X., Ma, X., He, Z., Wang, Y., Gerstein, M., Wang, R., Liu, G., and Zhao, H. (2025c). Igniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents. ACM Comput. Surv., 57.
Çımen, S., Karahan, S. N., Karhan, D., Güllü, M., and Osmanca, M. S. (2025). The Integration of Agentic AI in 6G Wireless Networks: State-of-the-Art, Challenges, and Future Perspectives. pages 1–6.
Alruqi, M., Hsairi, L., and Eshmawi, A. (2021). Secure mobile agents for patient status telemonitoring using blockchain. page 224–228.
Baradarannia, M., Hashemzadeh, F., and Kumbasar, T. (2025). Fixed-time surrounding control of multi-agent systems underdenial-of-service attacks. JOURNAL OF THE FRANKLIN INSTITUTE, 362.
Barambones, J., Richoux, F., Imbert, R., and Inoue, K. (2021). Resilient Team Formation with Stabilisability of Agent Networks for Task Allocation. ACM Trans. Auton. Adapt. Syst., 15.
Choi, I.-S., Hong, J., and Kim, T.-W. (2020). Multi-Agent Based Cyber Attack Detection and Mitigation for DistributionAutomation System. IEEE ACCESS, 8:183495–183504.
Damle, S., Triastcyn, A., Faltings, B., and Gujar, S. (2022). Differentially Private Multi-Agent Constraint Optimization. page 422–429.
de la Hoz, E., Gimenez-Guzman, J. M., Marsa-Maestre, I., Cruz-Piris, L., and Orden, D. (2017). A Distributed, Multi-Agent Approach to Reactive Network Resilience. page 1044–1053.
Deng, F., Xu, C., Guan, Z.-H., and Chen, G. (2024). Dynamic event-triggered quantized secure output consensus ofheterogeneous multi-agent systems under DoS attacks. CHAOS, 34.
Esmaeili, A., Ghorrati, Z., and Matson, E. T. (2024). Holonic Learning: A Flexible Agent-based Distributed Machine Learning Framework. page 525–533.
Felizardo, K. et al. (2017). Revisão sistemática da literatura em engenharia de software: teoria e prática. Elsevier Brasil.
Gao, R. and Yang, G.-H. (2024). Trust-Based Distributed Secure State Estimation Against Malicious Agentsvia Two-Hop Communication. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 69:1006–1013.
Hajar, M. S., Kalutarage, H. K., and Al-Kadri, M. (2023). 3R: A reliable multi agent reinforcement learning based routing protocolfor wireless medical sensor networks. COMPUTER NETWORKS, 237.
Hao, Q., Luo, M., Cheng, J., and Shi, K. (2025). Distributed fault-tolerant consensus for two-time-scale multiagentsystems against multiple faults and random attacks via a generalizedtwo-step transmission mechanism. JOURNAL OF THE FRANKLIN INSTITUTE, 362.
He, W., Xu, W., Ge, X., Han, Q.-L., Du, W., and Qian, F. (2022). Secure Control of Multiagent Systems Against Malicious Attacks: A BriefSurvey. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 18:3595–3608.
Huang, X. and Dong, J. (2020). Reliable Leader-to-Follower Formation Control of Multiagent SystemsUnder Communication Quantization and Attacks. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 50:89–99.
Jain, G. and Solomon Jebaraj, N. R. (2023). Taxonomy of Multi-Agent Systems Attacks and their Defense Tactics in Certifying Security of Cyber Physical Systems. pages 648–652.
Kott, A. (2023). Autonomous Intelligent Cyber Defense Agent (AICA): A Comprehensive Guide, volume 87 of Advances in Information Security. Springer.
Li, Y., Fang, H., and Chen, J. (2020). Anomaly Detection and Identification for Multiagent Systems Subjected toPhysical Faults and Cyberattacks. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 67:9724–9733.
Lin, B.-Y., Dziubałtowska, D., Macek, P., Penzkofer, A., and Müller, S. (2023). Tangle-Sim: An Agent-based, Modular Simulator for DAG-based Distributed Ledger Technologies. pages 1–5.
Lin, H., Dong, J., and Park, J. H. (2025). An Artificial-Delay-Based Looped Functional for Dynamic Event-Triggered Fault-Tolerant Control of T-S Fuzzy Multi-Agent Systems. IEEE Transactions on Automation Science and Engineering, 22:6050–6060.
Lu, C., Zhu, J., and Ouyang, L. (2024). Mission Reliability and Optimization in Multi-Agent Systems Using Hyperledger Fabric Platform. pages 1–6.
Lygizou, Z. and Kalles, D. (2025). A Biologically Inspired Trust Model for Open Multi-Agent Systems That IsResilient to Rapid Performance Fluctuations. APPLIED SCIENCES-BASEL, 15.
Mao, Y., Kang, Y., Li, P., Zhang, N., Xu, W., and Zhang, C. (2025). IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. page 2654–2656.
Marques, R. S., Epiphaniou, G., Al-Khateeb, H., Maple, C., Hammoudeh, M., De Castro, P. A. L., Dehghantanha, A., and Choo, K. K. R. (2021). A Flow-based Multi-agent Data Exfiltration Detection Architecture for Ultra-low Latency Networks. ACM Trans. Internet Technol., 21.
Masters, C., Vellanki, A., Shangguan, J., Kultys, B., Gilmore, J., Moore, A., and Albrecht, S. (2025). Orchestrating Human-AI Teams: The Manager Agent as aUnifying Research Challenge. page 91–107.
Phiri, C. C. (2025). Creating Characteristically Auditable Agentic AI Systems. page 1–14.
Pretila, H., Campbell, B., and Szabo, C. (2024). Contested Communication in C2 Multi-agent Simulations. page 25–29.
Toumi, H., Marzak, B., Khazri, Y., Talea, A., Eddaoui, A., and Talea, M. (2017). Mobiles Agents and Virtual Firewall to Secure the Shared Network for Virtual Machines in IaaS cloud.
Wen, X., Wen, J., Xiao, M., Kang, J., Zhang, T., Li, X., Chen, C., and Niyato, D. (2026). Defending Against Network Attacks for Secure AI Agent Migration in Vehicular Metaverses. IEEE Internet of Things Journal, 13:4153–4166.
Xue, W., Qiu, W., An, B., Rabinovich, Z., Obraztsova, S., and Yeo, C. K. (2022). Misspoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning. page 1418–1426.
Yuan, T., Chung, H.-M., and Fu, X. (2024). PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications. IEEE Network, 38:196–203.
Zhang, S., Ma, Y., Chen, J., Li, S., Yi, X., and Li, H. (2025a). Towards Aligning Personalized AI Agents with Users’ Privacy Preference. page 33–42.
Zhang, X., Dong, X., Wang, Y., Zhang, D., and Cao, F. (2025b). A Survey of Multi-AI Agent Collaboration: Theories, Technologies and Applications. page 1875–1881.
Zhang, Z., Yao, Y., Zhang, A., Tang, X., Ma, X., He, Z., Wang, Y., Gerstein, M., Wang, R., Liu, G., and Zhao, H. (2025c). Igniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents. ACM Comput. Surv., 57.
Çımen, S., Karahan, S. N., Karhan, D., Güllü, M., and Osmanca, M. S. (2025). The Integration of Agentic AI in 6G Wireless Networks: State-of-the-Art, Challenges, and Future Perspectives. pages 1–6.
Publicado
19/10/2026
Como Citar
SILVA, Michael da; SILVA, Anderson Aparecido Alves da.
Systematic Review of Reliability and Trustworthiness on Multi-Agent Architectures. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 20. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 252-263.
ISSN 2326-5434.
DOI: https://doi.org/10.5753/wesaac.2026.31909.
