{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T14:45:45Z","timestamp":1782571545259,"version":"3.54.5"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swinburne University of Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Inf. Secur."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Generative agents are a novel AI agent architecture developed in 2023 using LLMs that can generate believable human behaviors. They are of significant importance in social simulation and human-computer interaction. However, there is a lack of research on the privacy and security issues that may arise from its subsequent application in society. Based on the Generative Agent framework, this paper reintroduces a personal information system, and a shared database, reconstructing the memory and reflection systems to realize a Lightweight Generative Agent framework (LGA). To fill the research gap in the field of privacy for Generative Agents, this paper simulates three scenarios with five agents to explore potential privacy and security issues. Based on observed privacy leaks, three defensive strategies are proposed: behavior guideline regulation, Multi-Agents cooperation, and step-back prompts. These strategies have reduced privacy leaks by more than 50.00% on average. For some privacy leaks with special simulation scenarios, it has even reduced privacy leaks by more than 80.00%. Additionally, through supplementary experiments, we demonstrate that LGA achieves better cost-effectiveness compared to the original Generative Agent framework. The analysis of privacy and security issues provides a reference for subsequent research on the safety of generative agents.<\/jats:p>","DOI":"10.1007\/s10207-026-01244-y","type":"journal-article","created":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T12:34:02Z","timestamp":1775392442000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LGA: lightweight design and privacy analysis of generative agents in social simulations"],"prefix":"10.1007","volume":"25","author":[{"given":"Yongjian","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanlun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,5]]},"reference":[{"key":"1244_CR1","unstructured":"Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al.: The rise and potential of large language model based agents: A survey. arXiv:2309.07864 (2023)"},{"key":"1244_CR2","unstructured":"Brown, T.B.: Language models are few-shot learners. arXiv:2005.14165 (2020)"},{"key":"1244_CR3","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. arXiv:2303.08774 (2023)"},{"issue":"2","key":"1244_CR4","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1109\/JAS.2024.124971","volume":"12","author":"X Zhu","year":"2025","unstructured":"Zhu, X., Zhou, W., Han, Q.-L., Ma, W., Wen, S., Xiang, Y.: When software security meets large language models: a survey. IEEE\/CAA J. Automatica Sinica 12(2), 317\u2013334 (2025)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"1244_CR5","doi-asserted-by":"crossref","unstructured":"Huang, C., Mees, O., Zeng, A., Burgard, W.: Visual language maps for robot navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 10608\u201310615 (2023). IEEE","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"1244_CR6","doi-asserted-by":"crossref","unstructured":"Murakhovs\u2019\u00a0ka, L., Laban, P., Xie, T., Xiong, C., Wu, C.-S.: Salespeople vs salesbot: Exploring the role of educational value in conversational recommender systems. arXiv:2310.17749 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.657"},{"key":"1244_CR7","unstructured":"Chen, D., Wang, H., Huo, Y., Li, Y., Zhang, H.: Gamegpt: Multi-agent collaborative framework for game development. arXiv:2310.08067 (2023)"},{"issue":"5","key":"1244_CR8","doi-asserted-by":"publisher","first-page":"4997","DOI":"10.1109\/TDSC.2024.3367737","volume":"21","author":"W Ma","year":"2024","unstructured":"Ma, W., Song, Y., Xue, M., Wen, S., Xiang, Y.: The \u201ccode\u2019\u2019 of ethics: a holistic audit of ai code generators. IEEE Trans. Dependable Secure Comput. 21(5), 4997\u20135013 (2024). https:\/\/doi.org\/10.1109\/TDSC.2024.3367737","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"1244_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3534441","author":"C Sheng","year":"2025","unstructured":"Sheng, C., Zhou, W., Ma, W., Zhu, X., Wen, S., Xiang, Y.: Network traffic fingerprinting for iiot device identification: a survey. IEEE Trans. Industr. Inf. (2025). https:\/\/doi.org\/10.1109\/TII.2025.3534441","journal-title":"IEEE Trans. Industr. Inf."},{"key":"1244_CR10","doi-asserted-by":"publisher","unstructured":"Nair, V., Schumacher, E., Tso, G., Kannan, A.: DERA: Enhancing large language model completions with dialog-enabled resolving agents. In: Naumann, T., Ben\u00a0Abacha, A., Bethard, S., Roberts, K., Bitterman, D. (eds.) Proceedings of the 6th Clinical Natural Language Processing Workshop, pp. 122\u2013161. Association for Computational Linguistics, Mexico City, Mexico (2024). https:\/\/doi.org\/10.18653\/v1\/2024.clinicalnlp-1.12 . https:\/\/aclanthology.org\/2024.clinicalnlp-1.12","DOI":"10.18653\/v1\/2024.clinicalnlp-1.12"},{"key":"1244_CR11","doi-asserted-by":"publisher","first-page":"4469","DOI":"10.1109\/TIFS.2025.3560557","volume":"20","author":"W Ma","year":"2025","unstructured":"Ma, W., Wang, D., Song, Y., Xue, M., Wen, S., Li, Z., Xiang, Y.: Trapnet: model inversion defense via trapdoor. IEEE Trans. Inf. Forensics Secur. 20, 4469\u20134483 (2025). https:\/\/doi.org\/10.1109\/TIFS.2025.3560557","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"1244_CR12","unstructured":"Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S.K.S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., Schmidhuber, J.: MetaGPT: Meta programming for a multi-agent collaborative framework. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=VtmBAGCN7o"},{"key":"1244_CR13","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: Interactive simulacra of human behavior. In: Proceedings of the 36th Annual Acm Symposium on User Interface Software and Technology, pp. 1\u201322 (2023)","DOI":"10.1145\/3586183.3606763"},{"key":"1244_CR14","doi-asserted-by":"crossref","unstructured":"Zhou, W., Zhu, X., Han, Q.-L., Li, L., Chen, X., Wen, S., Xiang, Y.: The security of using large language models: A survey with emphasis on chatgpt. IEEE\/CAA Journal of Automatica Sinica (2024)","DOI":"10.1109\/JAS.2024.124983"},{"key":"1244_CR15","doi-asserted-by":"crossref","unstructured":"Nyffenegger, A., St\u00fcrmer, M., Niklaus, J.: Anonymity at risk? assessing re-identification capabilities of large language models in court decisions. In: Findings of the Association for Computational Linguistics: NAACL 2024, pp. 2433\u20132462 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.157"},{"key":"1244_CR16","doi-asserted-by":"publisher","unstructured":"Li, H., Guo, D., Fan, W., Xu, M., Huang, J., Meng, F., Song, Y.: Multi-step jailbreaking privacy attacks on ChatGPT. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 4138\u20134153. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.272 . https:\/\/aclanthology.org\/2023.findings-emnlp.272","DOI":"10.18653\/v1\/2023.findings-emnlp.272"},{"key":"1244_CR17","unstructured":"Elphinstone, K., Heiser, G., Liedtke, J.: Page tables for 64-bit computer systems. University of New South Wales School of Computer Science and Engineering (1998)"},{"key":"1244_CR18","doi-asserted-by":"publisher","unstructured":"Perez, E., Ringer, S.e.a.: Discovering language model behaviors with model-written evaluations. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguistics: ACL 2023, pp. 13387\u201313434. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.847 . https:\/\/aclanthology.org\/2023.findings-acl.847","DOI":"10.18653\/v1\/2023.findings-acl.847"},{"issue":"7","key":"1244_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3716628","volume":"57","author":"Z Deng","year":"2025","unstructured":"Deng, Z., Guo, Y., Han, C., Ma, W., Xiong, J., Wen, S., Xiang, Y.: AI agents under threat: a survey of key security challenges and future pathways. ACM Comput. Sur. 57(7), 1\u201336 (2025). https:\/\/doi.org\/10.1145\/3716628","journal-title":"ACM Comput. Sur."},{"key":"1244_CR20","unstructured":"Perez, F., Ribeiro, I.: Ignore previous prompt: Attack techniques for language models. (2022)"},{"key":"1244_CR21","doi-asserted-by":"publisher","unstructured":"Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., Fritz, M.: Not what you\u2019ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection. In: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security. AISec \u201923, pp. 79\u201390. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3605764.3623985","DOI":"10.1145\/3605764.3623985"},{"key":"1244_CR22","unstructured":"Wolf, Y., Wies, N., Levine, Y., Shashua, A.: Fundamental limitations of alignment in large language models. arXiv:2304.11082 (2023)"},{"key":"1244_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, F., Xu, Z., Niu, L., Wang, B., Jia, J., Li, B., Poovendran, R.: Identifying and mitigating vulnerabilities in llm-integrated applications. The Twelfth International Conference on Learning Representations (2023)","DOI":"10.1145\/3634737.3659433"},{"key":"1244_CR24","doi-asserted-by":"crossref","unstructured":"Mireshghallah, F., Uniyal, A., Wang, T., Evans, D.K., Berg-Kirkpatrick, T.: An empirical analysis of memorization in fine-tuned autoregressive language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 1816\u20131826 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.119"},{"key":"1244_CR25","unstructured":"Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., : Extracting training data from large language models. In: 30th USENIX Security Symposium (USENIX Security 21), pp. 2633\u20132650 (2021)"},{"key":"1244_CR26","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)"},{"issue":"5","key":"1244_CR27","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1109\/JAS.2025.125498","volume":"12","author":"Z Deng","year":"2025","unstructured":"Deng, Z., Ma, W., Han, Q.-L., Zhou, W., Zhu, X., Wen, S., Xiang, Y.: Exploring deepseek: A survey on advances, applications, challenges and future directions. IEEE\/CAA Journal of Automatica Sinica 12(5), 872\u2013893 (2025)","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"1244_CR28","doi-asserted-by":"publisher","first-page":"7211","DOI":"10.1109\/TIFS.2025.3581103","volume":"20","author":"Z Deng","year":"2025","unstructured":"Deng, Z., Sun, R., Xue, M., Ma, W., Wen, S., Nepal, S., Xiang, Y.: Hardening llm fine-tuning: from differentially private data selection to trustworthy model quantization. IEEE Trans. Inf. Forensics Secur. 20, 7211\u20137226 (2025). https:\/\/doi.org\/10.1109\/TIFS.2025.3581103","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"1244_CR29","doi-asserted-by":"crossref","unstructured":"Lukas, N., Salem, A., Sim, R., Tople, S., Wutschitz, L., Zanella-B\u00e9guelin, S.: Analyzing leakage of personally identifiable information in language models. arXiv:2302.00539 (2023)","DOI":"10.1109\/SP46215.2023.10179300"},{"key":"1244_CR30","doi-asserted-by":"publisher","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. In: Moens, M.-F., Huang, X., Specia, L., Yih, S.W.-t. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3784\u20133803. Association for Computational Linguistics, Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.320 . https:\/\/aclanthology.org\/2021.findings-emnlp.320","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"1244_CR31","doi-asserted-by":"crossref","unstructured":"Huang, X., Ruan, W., Huang, W., Jin, G., Dong, Y., Wu, C., Bensalem, S., Mu, R., Qi, Y., Zhao, X., et al.: A survey of safety and trustworthiness of large language models through the lens of verification and validation. arXiv:2305.11391 (2023)","DOI":"10.1007\/s10462-024-10824-0"},{"key":"1244_CR32","doi-asserted-by":"crossref","unstructured":"Yue, X., Wang, B., Chen, Z., Zhang, K., Su, Y., Sun, H.: Automatic evaluation of attribution by large language models. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/openreview.net\/forum?id=jVa7tFQw9N","DOI":"10.18653\/v1\/2023.findings-emnlp.307"},{"key":"1244_CR33","unstructured":"Tan, W., Zhang, W., Liu, S., Zheng, L., Wang, X., An, B.: True knowledge comes from practice: Aligning large language models with embodied environments via reinforcement learning. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=hILVmJ4Uvu"},{"issue":"12","key":"1244_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y.J., Madotto, A., Fung, P.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"1244_CR35","unstructured":"Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., et al.: Siren\u2019s song in the ai ocean: A survey on hallucination in large language models. arXiv:2309.01219 (2023)"},{"key":"1244_CR36","doi-asserted-by":"publisher","first-page":"34586","DOI":"10.52202\/068431-2506","volume":"35","author":"N Lee","year":"2022","unstructured":"Lee, N., Ping, W., Xu, P., Patwary, M., Fung, P.N., Shoeybi, M., Catanzaro, B.: Factuality enhanced language models for open-ended text generation. Adv. Neural. Inf. Process. Syst. 35, 34586\u201334599 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1244_CR37","doi-asserted-by":"crossref","unstructured":"Hase, P., Diab, M., Celikyilmaz, A., Li, X., Kozareva, Z., Stoyanov, V., Bansal, M., Iyer, S.: Methods for measuring, updating, and visualizing factual beliefs in language models. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2714\u20132731 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.199"},{"key":"1244_CR38","unstructured":"Ranaldi, L., Pucci, G.: When large language models contradict humans? large language models\u2019 sycophantic behaviour. arXiv:2311.09410 (2023)"},{"key":"1244_CR39","unstructured":"Wang, J., Hu, X., Hou, W., Chen, H., Zheng, R., Wang, Y., Yang, L., Huang, H., Ye, W., Geng, X., et al.: On the robustness of chatgpt: An adversarial and out-of-distribution perspective. The Eleventh International Conference on Learning Representations (2023)"},{"key":"1244_CR40","unstructured":"Williams, R., Hosseinichimeh, N., Majumdar, A., Ghaffarzadegan, N.: Epidemic modeling with generative agents. arXiv:2307.04986 (2023)"},{"key":"1244_CR41","unstructured":"Li, J., Wang, S., Zhang, M., Li, W., Lai, Y., Kang, X., Ma, W., Liu, Y.: Agent hospital: A simulacrum of hospital with evolvable medical agents. arXiv:2405.02957 (2024)"},{"key":"1244_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chiu, Y.Y., Chiu, Y.C.: Humanoid agents: Platform for simulating human-like generative agents. arXiv:2310.05418 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.15"},{"key":"1244_CR43","doi-asserted-by":"publisher","unstructured":"Zhang, A., Chen, Y., Sheng, L., Wang, X., Chua, T.-S.: On generative agents in recommendation. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201924, pp. 1807\u20131817. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657844","DOI":"10.1145\/3626772.3657844"},{"key":"1244_CR44","unstructured":"Yang, Z., Zhang, Z., Zheng, Z., Jiang, Y., Gan, Z., Wang, Z., Ling, Z., Chen, J., Ma, M., Dong, B., et al.: Oasis: Open agents social interaction simulations on one million agents. arXiv:2411.11581 (2024)"},{"key":"1244_CR45","unstructured":"Code of professional conduct and behavioral standards for banking practitioners. China Banking (09), 95\u201399 (2020)"},{"key":"1244_CR46","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., Mordatch, I.: Improving factuality and reasoning in language models through multiagent debate. In: Forty-first International Conference on Machine Learning (2023)"},{"key":"1244_CR47","unstructured":"Hu, B., Zhao, C., Zhang, P., Zhou, Z., Yang, Y., Xu, Z., Liu, B.: Enabling intelligent interactions between an agent and an llm: A reinforcement learning approach. arXiv:2306.03604 (2023)"},{"key":"1244_CR48","unstructured":"Zheng, H.S., Mishra, S., Chen, X., Cheng, H.-T., Chi, E.H., Le, Q.V., Zhou, D.: Take a step back: Evoking reasoning via abstraction in large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"1244_CR49","unstructured":"Labs, P.: Welcome to Phaser 3. https:\/\/phaser.io\/phaser3 (2023)"},{"key":"1244_CR50","unstructured":"pixlab: Top-down Pixel JRPG City Modular NPC Animation Asset Pack (2024). https:\/\/pixlab24.com\/character\/21638\/"}],"container-title":["International Journal of Information Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10207-026-01244-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10207-026-01244-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10207-026-01244-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T13:49:26Z","timestamp":1782568166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10207-026-01244-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,5]]},"references-count":50,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["1244"],"URL":"https:\/\/doi.org\/10.1007\/s10207-026-01244-y","relation":{},"ISSN":["1615-5270"],"issn-type":[{"value":"1615-5270","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,5]]},"assertion":[{"value":"22 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"77"}}