Security in Multi-Agent Systems
Open accessAbstract
Multi-agent systems become more and more popular due to successful implementations in different fields. However, there is a number of threats that can compromise security of the agent and jeopardize systems security. Therefore, security issues should be taken into consideration during development of multi-agent systems. However, different existing methodologies that provide guidelines and models for development of multi-agent systems omit security. Therefore, there is a great need in offering security solutions which are integrated with system functionalities. This research presents a model for securing multi-agent systems, which is developed, based on the concepts and models regarding agent's role and communications. Moreover, possible attacks on multi-agent systems are presented and threats are categorized. Furthermore, general security requirements at the agent and the system levels are defined and considered in the proposed model.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Earlier multi-agent system security frameworks primarily target symbolic agents and structured protocols, whereas our scope includes heterogeneous AI agents, humans, and institutions interacting over unstructured channels at scale.
“Earlier multi-agent system security frameworks (Hedin & Moradian, 2015) primarily target symbolic agents and structured protocols (e.g., access control, trust management), whereas our scope includes heterogeneous AI agents, humans, and institutions interacting over unstructured channels at scale.”
From Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents (2025) · cites this paper as Hedin & Moradian, 2015
Section 3 (Gaia methodology and multi-agent systems; page unavailable) describes software agents with defined roles, permissions, and interaction protocols. Sections 5.2 and 6 address authentication, unauthorized access, and secure agent communication. The paper does not characterize earlier frameworks as primarily targeting *symbolic* agents, and its related-work section also mentions human agents; the citing authors’ description of their own broader scope is not attributed to this source. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 15
- BELLIFEMINE, F., CAIRE, G., and GREENWOOD, D. (2007). Developing Multi-Agent Systems with JADE. West Sussex: John Wiley & Sons Ltd.
- BIJANI, Shahriar; ROBERTSON, David. A review of attacks and security approaches in open multi-agent systems. Artificial Intelligence Review, 2014, 42.4: 607-636.
- BISHOP, M. (2013). Introduction to Computer Security. Boston: Pearson Education Inc.
- BORSELIUS, Niklas. Security in multi-agent systems. In: Proceedings of the 2002 International Conference on Security and Management (SAM'02). 2002. p. 31-36.
- BRESCIANI, Paolo, et al. Multi-agent systems and security requirements analysis. In: Software Engineering for Multi-Agent Systems II. Springer Berlin Heidelberg, 2004. p. 35-48.
- CREMONINI, Marco; OMICINI, Andrea; ZAMBONELLI, Franco. Multi-agent systems on the Internet: Extending the scope of coordination towards security and topology. In: Multi-Agent System Engineering. Springer Berlin Heidelberg, 1999. p. 77-88.
- JENNINGS NR., SYCARA, K., WOOLDRIDGE, M. (1998). A roadmap of agent research and development, Auton Agents Multi Agent Syst 1(1):7-38.
- JUNG, Youna, et al. A survey of security issue in multi-agent systems.Artificial Intelligence Review, 2012, 37.3: 239-260.
- MORADIAN, Esmiralda. Security of e-commerce software systems. In: Agent and Multi-Agent Systems in Distributed Systems-Digital Economy and E-Commerce. Springer Berlin Heidelberg, 2013. p. 95-103.
- MORADIAN, Esmiralda; HÅKANSSON, Anne. Software Security Engineering Monitoring and Control. In: SAM 2011 The 2011 International Conference on Security and Management (WorldComp 2011). CSREA Press, USA. 2011.
- MOURATIDIS, Haralambos; GIORGINI, Paolo; MANSON, Gordon. Modelling secure multiagent systems. In: Proceedings of the second international joint conference on Autonomous agents and multiagent systems. ACM, 2003. p. 859-866.
- STURM, Arnon; SHEHORY, Onn. A framework for evaluating agent-oriented methodologies. In: Agent-Oriented Information Systems. Springer Berlin Heidelberg, 2004. p. 94-109.
- VIEGA, John; BLOCH, J. T.; CHANDRA, Pravir. Applying aspect-oriented programming to security. Cutter IT Journal, 2001, 14.2: 31-39.
- WOOLDRIDGE, M., JENNINGS, N. R., & KINNY, D. A methodology for Agent-oritented Analysis and Design. Processing of the Thrid International Conference on Autonomous Agents(Agents 99,1999. P. 69-76.
- ZAMBONELLI, Franco; JENNINGS, Nicholas R.; WOOLDRIDGE, Michael. Developing multiagent systems: The Gaia methodology. ACM Transactions on Software Engineering and Methodology (TOSEM), 2003, 12.3: 317-370.
Cited by
Sorted by citations
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
de Witt, C. S., Krawiecka, K., Krawczuk, I., Hagag, B., Anderson, W. L., Belcak, P., Bucknall, B., Cai, X., Chopra, A., Cohen, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.02077 · Cited by 2 · see citing works
- Authors
- Hedin, Y., & Moradian, E.
- Affiliations
- Stockholm University (SE)
- Corresponding author
- Hedin, Yaqin
- Venue
- Procedia Computer Science
- Publisher
- Elsevier BV
- Published
- 2015
- Volume
- 60
- Pages
- 1604-1612
- ISSN
- 1877-0509 (ISSN-L)
- OpenAlex
- W2399345027
- Cited by
- 49
- References
- 0
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 4 · 2023: 4 · 2022: 7 · 2021: 2 · 2020: 4 · 2019: 10 · 2018: 9 · 2017: 1 · 2016: 3
- FWCI
- 15.78
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Procedia Computer Science (publishedVersion, cc-by-nc-nd)
- Topics
- Social Sciences › Sociology and Political Science › Access Control and Trust
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Computer Science › Computer Networks and Communications › Mobile Agent-Based Network Management
- Keywords
- multi-agent systems, security (computing), agent security, security threats, threat categorization, security requirements, agent roles, agent communication, security model
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
