A Game-Theoretic Approach to Containing Artificial General Intelligence: Insights From Highly Autonomous Aggressive Malware
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Artificial general intelligence (AGI) promises transformative societal changes but poses safety and containment challenges. Large language models such as ChatGPT have intensified public expectations and apprehensions regarding AGI capabilities and risks. Existing research underestimated replicating human intelligence and lacks effective containment strategies scaled for AGI's complexity. We developed a cybersecurity-inspired framework to reconceptualize AGI containment as securing critical infrastructure indispensable for its operation. We applied game theory to model the strategic interplay between AGI and humans, drawing parallels with highly autonomous malware, emphasizing infrastructural dependencies and human countermeasures. We introduced offensive/defensive containment strategies and an AGI Kill Chain model profiling escalating AGI threats. Our game-theoretic approach examined complex AGI-human interactions revealing insights for adaptive oversight mechanisms. Game simulations demonstrated AGI carefully manages resources and autonomy balancing benefits against risks, necessitating strategic human responses. Our findings provided detailed containment tactics, emphasizing flexibility to address AGI's dynamic evolution. We proposed comprehensive, multidisciplinary containment strategies, effective governance evaluating long-term efficacy, and emphasize ongoing innovation for aligning AGI progression with utility and security.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Levels of AGI for Operationalizing Progress on the Path to AGI
Morris, M. R., Sohl-Dickstein, J., Fiedel, N., Warkentin, T., Dafoe, A., Faust, A., Farabet, C., & Legg, S. (2023) · arXiv · doi:10.48550/arxiv.2311.02462 · Cited by 274
The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents
Bostrom, N. (2012) · Minds and Machines · doi:10.1007/s11023-012-9281-3 · Cited by 254
McIntosh, T., Kayes, A. S. M., Chen, Y.-P. P., Ng, A., & Watters, P. (2022) · ACM Computing Surveys · doi:10.1145/3479393 · Cited by 146
Self-citationA Culturally Sensitive Test to Evaluate Nuanced GPT Hallucination
McIntosh, T. R., Liu, T., Susnjak, T., Watters, P., Ng, A., & Halgamuge, M. N. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3332837 · Cited by 145 · cited 1×
“…potential impacts on job markets, privacy concerns, and ethical considerations related to autonomy and agency, underlining the importance of balancing technological advancement with societal welfare, and ensuring that AGI development aligns with ethical norms and societal values [7], [8], [9].”
Self-citationResponses to catastrophic AGI risk: a survey
Sotala, K., & Yampolskiy, R. V. (2015) · Physica Scripta · doi:10.1088/0031-8949/90/1/018001 · Cited by 121 · cited 1×
“Sotala and Yampolskiy highlighted AGI’s potential for catastrophic risks due to increasing power and autonomy [27].”
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., & Halgamuge, M. N. (2024) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2024.3377445 · Cited by 62 · cited 1×
“…potential impacts on job markets, privacy concerns, and ethical considerations related to autonomy and agency, underlining the importance of balancing technological advancement with societal welfare, and ensuring that AGI development aligns with ethical norms and societal values [7], [8], [9].”
Self-citation
Cited by
Mapping the ethics of generative AI: a comprehensive scoping review
Hagendorff, T. (2024) · Minds and Machines · doi:10.1007/s11023-024-09694-w · Cited by 141
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102
Self-citationAI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents
Karim, M. M., Van, D. H., Khan, S., Qu, Q., & Kholodov, Y. (2025) · Future Internet · doi:10.3390/fi17020057 · Cited by 73
Metadata
- Authors
- McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Ng, A., & Halgamuge, M. N.
- Venue
- IEEE Transactions on Artificial Intelligence
- Published
- 2024-12
- Volume
- 5
- Issue
- 12
- Pages
- 6290-6303
- ISSN
- 2691-4581 (ISSN-L)
- OpenAlex
- W4396534976
- Cited by
- 37
- References
- 6
- FWCI
- 15.27
- Type
- journal article
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Game-Theoretic Approach to Containing Artificial General Intelligence: Insights From Highly Autonomous Aggressive Malware. https://app.cochat.ai/papers/10.1109/tai.2024.3394392
- The paper
- McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Ng, A., & Halgamuge, M. N. (2024). A Game-Theoretic Approach to Containing Artificial General Intelligence: Insights From Highly Autonomous Aggressive Malware. IEEE Transactions on Artificial Intelligence. https://doi.org/10.1109/tai.2024.3394392
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.