{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:19:12Z","timestamp":1773155952535,"version":"3.50.1"},"reference-count":73,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002631","name":"Korea Agency for Technology and Standards","doi-asserted-by":"publisher","award":["1415181629"],"award-info":[{"award-number":["1415181629"]}],"id":[{"id":"10.13039\/501100002631","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002631","name":"Korea Agency for Technology and Standards","doi-asserted-by":"publisher","award":["1415180835"],"award-info":[{"award-number":["1415180835"]}],"id":[{"id":"10.13039\/501100002631","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In recent years, the rapid growth of cryptocurrency markets has highlighted the urgent need for advanced security solutions capable of addressing a spectrum of unique threats, from phishing and wallet hacks to complex blockchain vulnerabilities. This paper presents a comprehensive approach to fortifying cryptocurrency systems by harnessing the structural symmetry inherent in transactional patterns. By leveraging local large language models (LLMs), embeddings, and vector databases, we develop an intelligent and scalable security expert system that exploits symmetry-based anomaly detection to enhance threat identification. Cryptocurrency networks face increasing threats from sophisticated attacks that often exploit asymmetric vulnerabilities. To counteract these risks, we propose a novel security expert system that integrates symmetry-aware analysis through LLMs and advanced embedding techniques. Our system efficiently captures symmetrical transaction patterns, enabling robust detection of anomalies and threats while preserving structural integrity. By integrating a modular framework with LangChain and a vector database (Chroma DB), we achieve improved accuracy, recall, and precision by leveraging the symmetry of transaction distributions and behavioral patterns. This work sets a new benchmark for LLM-driven cybersecurity solutions, offering a scalable and adaptive approach to reinforcing the security symmetry in cryptocurrency systems. The proposed expert system was evaluated using a benchmark dataset of cryptocurrency transactions, including real-world threat scenarios involving phishing, fraudulent transactions, and blockchain anomalies. The system achieved an accuracy of 92%, a precision of 89%, and a recall of 93%, demonstrating a 10% improvement over existing security frameworks. Compared to traditional rule-based and machine learning-based detection methods, our approach significantly enhances real-time threat detection while reducing false positives. The integration of LLMs with embeddings and vector retrieval enables more efficient contextual anomaly detection, setting a new benchmark for AI-driven security solutions in the cryptocurrency domain.<\/jats:p>","DOI":"10.3390\/sym17040496","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:17:14Z","timestamp":1742962634000},"page":"496","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Cryptocurrency Security: Leveraging Embeddings and Large Language Models for Creating Cryptocurrency Security Expert Systems"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3605-5295","authenticated-orcid":false,"given":"Ahmed A.","family":"Abdallah","sequence":"first","affiliation":[{"name":"Faculty of Information Technology and Computer Science, Nile University, Cairo 12588, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0821-5378","authenticated-orcid":false,"given":"Heba K.","family":"Aslan","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Computer Science, Nile University, Cairo 12588, Egypt"},{"name":"Informatics Department, Electronics Research Institute (ERI), Cairo 11843, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7351-625X","authenticated-orcid":false,"given":"Mohamed S.","family":"Abdallah","sequence":"additional","affiliation":[{"name":"Informatics Department, Electronics Research Institute (ERI), Cairo 11843, Egypt"},{"name":"AI Laboratory, DeltaX Co., Ltd., 5F, 590 Gyeongin-ro, Guro-gu, Seoul 08213, Republic of Korea"},{"name":"Department of Computer Engineering, Gachon University, Seongnam 13415, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0184-7599","authenticated-orcid":false,"given":"Young-Im","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam 13415, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8068-5120","authenticated-orcid":false,"given":"Marianne A.","family":"Azer","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Computer Science, Nile University, Cairo 12588, Egypt"},{"name":"National Telecommunication Institute, Cairo 12578, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,26]]},"reference":[{"key":"ref_1","unstructured":"He, Z., Li, Z., Yang, S., Qiao, A., Zhang, X., Luo, X., and Chen, T. (2024). Large Language Models for Blockchain Security: A Systematic Literature Review. arXiv."},{"key":"ref_2","unstructured":"Yu, J. (2024). Retrieval Augmented Generation Integrated Large Language Models in Smart Contract Vulnerability Detection. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Geren, C., Board, A., Dagher, G.G., Andersen, T., and Zhuang, J. (2024). Blockchain for Large Language Model Security and Safety: A Holistic Survey. arXiv.","DOI":"10.1145\/3715073.3715075"},{"key":"ref_4","unstructured":"Azad, P., Akcora, C.G., and Khan, A. (2024). Machine Learning for Blockchain Data Analysis: Progress and Opportunities. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Trozze, A., Davies, T., and Kleinberg, B. (2024). Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?. Artif. Intell. Law, 1\u201347.","DOI":"10.1007\/s10506-024-09399-6"},{"key":"ref_6","unstructured":"Kheddar, H. (2024). Transformers and large language models for efficient intrusion detection systems: A comprehensive survey. arXiv."},{"key":"ref_7","unstructured":"Gai, Y., Zhou, L., Qin, K., Song, D., and Gervais, A. (2023). Blockchain large language models. arXiv."},{"key":"ref_8","first-page":"4","article-title":"AI-powered Fraud Detection in Decentralized Finance: A Project Life Cycle Perspective","volume":"57","author":"Luo","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Arikkat, D.R., Abhinav, M., Binu, N., Parvathi, M., Navya, B., Arunima, K.S., Vinod, P., Rafidha Rehiman, K.A., and Conti, M. (2024, January 22\u201323). IntellBot: Retrieval Augmented LLM Chatbot for Cyber Threat Knowledge Delivery. Proceedings of the IEEE 16th International Conference on Computational Intelligence and Communication Networks (CICN), Indore, India.","DOI":"10.1109\/CICN63059.2024.10847404"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Weichbroth, P., Wereszko, K., Anacka, H., and Kowal, J. (2023). Security of Cryptocurrencies: A View on the State-of-the-Art Research and Current Developments. Sensors, 23.","DOI":"10.3390\/s23063155"},{"key":"ref_11","unstructured":"(2025, January 25). sanctions.io. Everything You Need to Know About Crypto Due Diligence in 2024. Available online: https:\/\/www.sanctions.io\/blog\/crypto-due-diligence."},{"key":"ref_12","unstructured":"John, F., and Dmytro, Y. (2024). Cryptocurrency Security Standard (CCSS)\u2014A Complete Guide, Hacken.io."},{"key":"ref_13","unstructured":"Behnke, R. (2024). A Guide to CCSS Audits: Ensuring Top-Notch Crypto Security, Halborn."},{"key":"ref_14","unstructured":"Valerioshi, X., Lim, V., and Khei, L.C. (2024). Master Guide To Crypto Security: Crypto Wallets, Smart Contracts, DeFi, And NFTs, CoinGecko."},{"key":"ref_15","unstructured":"Arkose Labs (2024). Guide to Cryptocurrency Security, Arkose Labs."},{"key":"ref_16","unstructured":"Stouffer, C. (2024). Cryptocurrency Security Guide + 9 Crypto Protection Tips, Norton."},{"key":"ref_17","unstructured":"Orcutt, M. (2024). How Secure is Blockchain Really?, MIT Technology Review."},{"key":"ref_18","unstructured":"Al Sabah, M. (2024). Cryptocurrency Isn\u2019t Private\u2014But With Know-How, It Could Be, MIT Technology Review."},{"key":"ref_19","unstructured":"Adams, J. (2024). CryptoCurrency Security Standard: The Full Compliance Guide, Doubloin."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Motlagh, F.N., Hajizadeh, M., Majd, M., Najafi, P., Cheng, F., and Meinel, C. (2024). Large Language Models in Cybersecurity: State-of-the-Art. arXiv.","DOI":"10.5220\/0013377600003899"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ranade, P., Piplai, A., Joshi, A., and Finin, T. (2021, January 15\u201318). CyBERT: Contextualized Embeddings for the Cybersecurity Domain. Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA.","DOI":"10.1109\/BigData52589.2021.9671824"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Jin, J., Tang, B., Ma, M., Liu, X., Wang, Y., Lai, Q., Yang, J., and Zhou, C. (2024). Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language Models. arXiv.","DOI":"10.1109\/ICCBD-AI65562.2024.00011"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ferrag, M.A., Alwahedi, F., Battah, A., Cherif, B., Mechri, A., and Tihanyi, N. (2024). Generative AI and Large Language Models for Cyber Security: All Insights You Need. arXiv.","DOI":"10.2139\/ssrn.4853709"},{"key":"ref_24","unstructured":"Wan, Z., Cheng, A., Wang, Y., and Wang, L. (2024). Information Leakage from Embedding in Large Language Models. arXiv."},{"key":"ref_25","unstructured":"Xu, H., Wang, S., Li, N., Wang, K., Zhao, Y., Chen, K., Yu, T., Liu, Y., and Wang, H. (2024). Large Language Models for Cyber Security: A Systematic Literature Review. arXiv."},{"key":"ref_26","unstructured":"Kyadige, A., and Taoufiq, S. (2025, January 25). Benchmarking the Security Capabilities of Large Language Models, Sophos News, Available online: https:\/\/news.sophos.com\/en-us\/2024\/03\/18\/benchmarking-the-security-capabilities-of-large-language-models\/."},{"key":"ref_27","unstructured":"Gennari, J., Lau, S.-h., Perl, S., Parish, J., and Sastry, G. (2025, January 25). Considerations for evaluating large language models for cybersecurity tasks, SEI Insights, Available online: https:\/\/www.cmu.edu\/news\/stories\/archives\/2024\/april\/sei-and-openai-recommend-ways-to-evaluate-large-language-models-for-cybersecurity-applications."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kucharavy, A., Plancherel, O., Mulder, V., Mermoud, A., and Lenders, V. (2024). Large Language Models in Cybersecurity: Threats, Exposure and Safety, Springer.","DOI":"10.1007\/978-3-031-54827-7"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sarker, I.H. (2024). Generative AI and Large Language Modeling in Cybersecurity. AI-Driven Cybersecurity and Threat Intelligence, Springer.","DOI":"10.1007\/978-3-031-54497-2"},{"key":"ref_30","unstructured":"(2023). Blockchain in Finance: Legislative and Regulatory Actions Are Needed to Ensure Comprehensive Oversight of Crypto Assets (Standard No. GAO-23-105346). Available online: https:\/\/www.gao.gov\/products\/gao-23-105346."},{"key":"ref_31","first-page":"58","article-title":"The Future of Crypto currency: Gaps, Challenges, and Concerns","volume":"24","author":"Zwilling","year":"2023","journal-title":"Issues Inf. Syst."},{"key":"ref_32","unstructured":"Hallman, R.A. (2025, January 25). Can Large Language Models Improve Security and Confidence in Decentralized Finance?, CAT Labs Blog, Available online: https:\/\/blog.catlabs.io\/can-large-language-models-improve-security-and-confidence-in-decentralized-finance\/."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s42521-020-00018-y","article-title":"Deep learning-based cryptocurrency sentiment construction","volume":"2","author":"Nasekin","year":"2020","journal-title":"Digit Financ."},{"key":"ref_34","unstructured":"Janakiram, M.S.V. (2025, January 25). The Building Blocks of LLMs: Vectors, Tokens, Embeddings, The New Stack, Available online: https:\/\/thenewstack.io\/the-building-blocks-of-llms-vectors-tokens-and-embeddings\/."},{"key":"ref_35","unstructured":"Collins, S. (2025, January 30). How to Build a System of Experts with LLMs, Stephen Collins.tech, Available online: https:\/\/dev.to\/stephenc222\/how-to-build-a-system-of-experts-with-llms-2gn6."},{"key":"ref_36","unstructured":"Neves, M.C. (2025, January 30). LLM Mixture of Experts Explained, TensorOps, Available online: https:\/\/www.tensorops.ai\/post\/what-is-mixture-of-experts-llm."},{"key":"ref_37","unstructured":"Xiao, Z., Zhang, D., Wu, Y., Xu, L., Wang, Y.J., Han, X., Fu, X., Zhong, T., Zeng, J., and Song, M. (2024, January 7\u201311). Chain-of-Experts: When LLMs Meet Complex Operations Research Problems. Proceedings of the 11th International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_38","unstructured":"Bornstein, M., and Radovanovic, R. (2023). Emerging Architectures for LLM Applications, Andreessen Horowitz. Available online: https:\/\/a16z.com\/emerging-architectures-for-llm-applications\/."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"19406","DOI":"10.1007\/s10489-023-04504-9","article-title":"Inspection-L: Self-supervised GNN node embeddings for money laundering detection in bitcoin","volume":"53","author":"Lo","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_40","unstructured":"Li, S., Zhou, J., Mo, C., Li, J., Tso, G.K.F., and Tian, Y. (2022). Motif-Aware Temporal GCN for Fraud Detection in Signed Cryptocurrency Trust Networks. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"McNally, S., Roche, J., and Caton, S. (2018, January 21\u201323). Predicting the Price of Bitcoin Using Machine Learning. Proceedings of the 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), Cambridge, UK.","DOI":"10.1109\/PDP2018.2018.00060"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"120838","DOI":"10.1016\/j.eswa.2023.120838","article-title":"PreBit\u2014A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin","volume":"233","author":"Zou","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3416","DOI":"10.1109\/COMST.2018.2842460","article-title":"A Survey on Security and Privacy Issues of Bitcoin","volume":"20","author":"Conti","year":"2018","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Kang, I., Mridul, M.A., Sanders, A., Ma, Y., Munasinghe, T., Gupta, A., and Seneviratne, O. (2024, January 21\u201324). Deciphering Crypto Twitter. Proceedings of the 16th ACM Web Science Conference, New York, NY, USA.","DOI":"10.1145\/3614419.3644026"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Anthony, N.T., Shafik, M., Kurugollu, F., and Atlam, H.F. (2022). Anomaly Detection in Ethereum Using Machine Learning. Anomaly Detection System for Ethereum Blockchain Using Machine Learning. Advances in Manufacturing Technology XXXV, IOS Press.","DOI":"10.3233\/ATDE220608"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s42786-018-00002-6","article-title":"A survey of blockchain from security perspective","volume":"3","author":"Dasgupta","year":"2019","journal-title":"J. Bank Financ. Technol."},{"key":"ref_47","unstructured":"Turner, A.B. (2022). Addressing The Intelligence Applications of Bitcoin Payments Related to Ransomware. [Ph.D.Thesis, Macquarie University]."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"23733","DOI":"10.1109\/ACCESS.2024.3363469","article-title":"Revolutionizing cyber threat detection with large language models: A privacy-preserving bert-based lightweight model for iot\/iiot devices","volume":"12","author":"Ferrag","year":"2024","journal-title":"IEEE Access"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ferrag, M.A., Alwahedi, F., Battah, A., Cherif, B., Mechri, A., Tihanyi, N., Bisztray, T., and Debbah, M. (2025). Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities. arXiv.","DOI":"10.1016\/j.iotcps.2025.01.001"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Omar, M. (2023). Detecting software vulnerabilities using Language Models. arXiv.","DOI":"10.1109\/CSR57506.2023.10224924"},{"key":"ref_51","unstructured":"Microsoft Security (2025, January 30). Staying Ahead of Threat Actors in the Age of AI. Microsoft Security Blog, 14 February 2024., Available online: https:\/\/www.microsoft.com\/en-us\/security\/blog\/2024\/02\/14\/staying-ahead-of-threat-actors-in-the-age-of-ai\/."},{"key":"ref_52","unstructured":"Shalom, E., and David, G. (2025, January 30). Self-enhancing pattern detection with LLMs: Our answer to uncovering malicious packages at scale, Apiiro Blog, Available online: https:\/\/apiiro.com\/blog\/llm-code-pattern-malicious-package-detection\/."},{"key":"ref_53","unstructured":"Hassanin, M., and Moustafa, N. (2024). A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1007\/s11263-024-02214-4","article-title":"Contextual object detection with multimodal large language models","volume":"133","author":"Zang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Sinha, R., Elhafsi, A., Agia, C., Foutter, M., Schmerling, E., and Pavone, M. (2024). Real-time anomaly detection and reactive planning with large language models. arXiv.","DOI":"10.15607\/RSS.2024.XX.114"},{"key":"ref_56","unstructured":"Antonopoulos, A.M. (2017). Mastering Bitcoin: Unlocking Digital Cryptocurrencies, O\u2019Reilly Media. [2nd ed.]."},{"key":"ref_57","unstructured":"Lewis, A. (2018). The Basics of Bitcoins and Blockchains: An Introduction to Cryptocurrencies and the Technology That Powers Them, Mango Media."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Burniske, C., and Tatar, J. (2017). Cryptoassets: The Innovative Investor\u2019s Guide to Bitcoin and Beyond, McGraw-Hill Education.","DOI":"10.15358\/9783800657360"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Drescher, D. (2017). Blockchain Basics: A Non-Technical Introduction in 25 Steps, Apress.","DOI":"10.1007\/978-1-4842-2604-9"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Ali, M., Fromm, M., Thellmann, K., Rutmann, R., L\u00fcbbering, M., Leveling, J., Klug, K., Ebert, J., Doll, N., and Buschhoff, J. (2024). Tokenizer choice for llm training: Negligible or crucial?. Findings of the Association for Computational Linguistics: NAACL 2024, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-naacl.247"},{"key":"ref_61","unstructured":"Chen, Y., and Wang, X. (2025, January 30). Understanding LLM Embeddings: A Comprehensive Guide, Irisagent Blog, Available online: https:\/\/irisagent.com\/blog\/understanding-llm-embeddings-a-comprehensive-guide\/."},{"key":"ref_62","unstructured":"Talamadupula, K. (2025, January 30). A Guide to LLM Inference Performance Monitoring, Symbl AI Blog, Available online: https:\/\/symbl.ai\/developers\/blog\/a-guide-to-llm-inference-performance-monitoring\/."},{"key":"ref_63","unstructured":"UbiOps (2025, January 30). How to Benchmark and Optimize LLM Inference Performance, UbiOps, Available online: https:\/\/ubiops.com\/benchmark-and-optimize-llm-inference-performance."},{"key":"ref_64","unstructured":"Agarwal, M., Qureshi, A., Sardana, N., Li, L., Quevedo, J., and Khudia, D. (2025, January 30). LLM Inference Performance Engineering: Best Practices, Databricks Blog, Available online: https:\/\/www.databricks.com\/blog\/llm-inference-performance-engineering-best-practices."},{"key":"ref_65","unstructured":"Jing, Z., Su, Y., and Han, Y. (2024). When Large Language Models Meet Vector Databases: A Survey. arXiv."},{"key":"ref_66","unstructured":"Pan, J.J., Wang, J., and Li, G. (2023). Survey of Vector Database Management Systems. arXiv."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Chavan, A., Magazine, R., Kushwaha, S., Debbah, M., and Gupta, D. (2024). Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward. arXiv.","DOI":"10.24963\/ijcai.2024\/883"},{"key":"ref_68","unstructured":"Ferrer, J. (2025, January 30). Optimizing Your LLM for Performance and Scalability, KDnuggets, Available online: https:\/\/www.kdnuggets.com\/optimizing-your-llm-for-performance-and-scalability."},{"key":"ref_69","unstructured":"Dholariya, F. (2025, January 30). Reducing High Computational Costs in LLMs: Effective Strategies for Sustainable, Dexoc Blog, Available online: https:\/\/dexoc.com\/blog\/reducing-high-computational-costs-in-llm."},{"key":"ref_70","unstructured":"Gupta, S., Kumar, R., and Roy, M. (2025, January 25). Data Drift in LLMs\u2014Causes, Challenges, Strategies, Nexla Blog, Available online: https:\/\/nexla.com\/ai-infrastructure\/data-drift\/."},{"key":"ref_71","unstructured":"Cui, J., Xu, Y., Huang, Z., Zhou, S., Jiao, J., and Zhang, J. (2024). Recent Advances in Attack and Defense Approaches of Large Language Models. arXiv."},{"key":"ref_72","unstructured":"Srinivasan, S., Mahbub, M., and Sadovnik, A. (2024). Advancing NLP Security by Leveraging LLMs as Adversarial Engines. arXiv."},{"key":"ref_73","unstructured":"Ribeiro, D. (2025, January 25). The Unspoken Challenges of Large Language Models, Deeper Insights Blog, Available online: https:\/\/deeperinsights.com\/ai-blog\/the-unspoken-challenges-of-large-language-models."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/496\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:00:19Z","timestamp":1760029219000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,26]]},"references-count":73,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["sym17040496"],"URL":"https:\/\/doi.org\/10.3390\/sym17040496","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,26]]}}}