Phishing Ataklarının Büyük Dil Modelleri Üzerine Etkileri
DOI:
https://doi.org/10.5281/zenodo.18213660Anahtar Kelimeler:
LLM tabanlı tehdit azaltma- Kimlik avı atakları- Yapay zeka tabanlı kimlik avıÖzet
Büyük dil modellerinin (LLM) yaygın olarak uygulanması, önemli akademik ve toplumsal ilgiyi çeken yeni güvenlik zorluklarını ve etik endişeleri artırmıştır. LLM'lerin güvenlik açıklarının ve siber suçlarda kötüye kullanımının analizi, gelişmiş metin oluşturma yeteneklerinin kişisel gizlilik, veri güvenliği ve bilgi bütünlüğü için ciddi tehditler oluşturduğunu ortaya koymaktadır. Ayrıca, mevcut LLM tabanlı savunma stratejilerinin etkinliği incelenmiş ve değerlendirilmiştir. Bu çalışma, LLM'lerin phishing ataklarına karşı sosyal etkilerini incelemekte ve alanın gelişimini bilgilendirmeyi amaçlayan güvenlik uygulamaları ile etik yönetişimlerini geliştirmek için gelecekteki uygulamaları önermektedir.
Referanslar
Afane, K., Wei, W., Mao, Y., Farooq, J., & Chen, J. (2024). Next-generation phishing: How LLM agents empower cyber attackers. In 2024 IEEE International Conference on Big Data (Big Data) (pp. 2558–2567). IEEE. https://doi.org/10.1109/BigData62323.2024.10825316
Alabdan, R. (2020). Phishing attacks survey: Types, vectors, and technical approaches. Future Internet, 12(10), 168. https://doi.org/10.3390/fi12100168
Altunay, H. C. (2024a). Detection of SQL Injection attacks using machine learning algorithms based on NLP-based feature extraction. In 9th International Conference on Computer Science and Engineering (UBMK) (pp. 468–472). IEEE. https://doi.org/10.1109/UBMK62933.2024.10756715
Altunay, H. C. (2024b). Analysis of cyber attacks using honeypot. Black Sea Journal of Engineering and Science, 7(5), 954–959. https://doi.org/10.52704/bsscience.1481075
Altunay, H. C., & Albayrak, Z. (2024). SMS spam detection system based on deep learning architectures for Turkish and English messages. Applied Sciences, 14(24), 11804. https://doi.org/10.3390/app142411804
Annepaka, Y., & Pakray, P. (2025). Large language models: A survey of their development, capabilities, and applications. Knowledge and Information Systems, 67(3), 2967–3022. https://doi.org/10.1007/s10115-024-02264-0
Bethany, M., Galiopoulos, A., Bethany, E., Karkevandi, M. B., Beebe, N., Vishwamitra, N., & Najafirad, P. (2025). Lateral phishing with large language models: A large organization comparative study. IEEE Access, 13, 60684–60701. https://doi.org/10.1109/ACCESS.2025.3526685
Bossetta, M. (2018). The weaponization of social media: Spear phishing and cyberattacks on democracy. Journal of International Affairs, 71(2), 97–106.
Boyd, S. W., & Keromytis, A. D. (2004). SQLrand: Preventing SQL injection attacks. In Applied Cryptography and Network Security (ACNS 2004) (pp. 292–302). Springer. https://doi.org/10.1007/978-3-540-24852-1_23
Das, B. C., Amini, M. H., & Wu, Y. (2025). Security and privacy challenges of large language models: A survey. ACM Computing Surveys, 57(6), 1–39. https://doi.org/10.1145/3690650
Geren, C., Board, A., Dagher, G. G., Andersen, T., & Zhuang, J. (2025). Blockchain for large language model security and safety: A holistic survey. ACM SIGKDD Explorations Newsletter, 26(2), 1–20. https://doi.org/10.1145/3706497.3706500
Hadnagy, C. (2010). Social engineering: The art of human hacking. John Wiley & Sons.
Khonji, M., Iraqi, Y., & Jones, A. (2013). Phishing detection: A literature survey. IEEE Communications Surveys & Tutorials, 15(4), 2091–2121. https://doi.org/10.1109/SURV.2013.032213.00001
Kulkarni, A., Balachandran, V., Divakaran, D. M., & Das, T. (2024). From ML to LLM: Evaluating the robustness of phishing webpage detection models against adversarial attacks. Digital Threats: Research and Practice, 6(2), 1–25. https://doi.org/10.1145/3696455
Quinn, T., & Thompson, O. (2024). Applying large language model (LLM) for developing cybersecurity policies to counteract spear phishing attacks on senior corporate managers [Preprint]. Research Square. https://doi.org/10.21203/rs.3.rs-4405206/v1
Salt, C. (2009). SQL injection attacks and defense. Elsevier (Syngress).
Wang, S., Zhao, Y., Hou, X., & Wang, H. (2025). Large language model supply chain: A research agenda. ACM Transactions on Software Engineering and Methodology, 34(5), 1–46. https://doi.org/10.1145/3702995
Xiao, X., Zhang, Y., Xu, J., Ren, W., & Zhang, J. (2025). Assessment methods and protection strategies for data leakage risks in large language models. Journal of Industrial Engineering and Applied Science, 3(2), 6–15.
Zheng, J., Qiu, S., Shi, C., & Ma, Q. (2025). Towards lifelong learning of large language models: A survey. ACM Computing Surveys, 57(8), 1–35. https://doi.org/10.1145/3703155
Zheng, X., Pang, T., Du, C., Liu, Q., Jiang, J., & Lin, M. (2024). Improved few-shot jailbreaking can circumvent aligned language models and their defenses. Advances in Neural Information Processing Systems (NeurIPS), 37, 32856–32887.
Zhu, X., Zhou, W., Han, Q. L., Ma, W., Wen, S., & Xiang, Y. (2025). When software security meets large language models: A survey. IEEE/CAA Journal of Automatica Sinica, 12(2), 317–334. https://doi.org/10.1109/JAS.2024.410762
İndir
Yayınlanmış
Nasıl Atıf Yapılır
Sayı
Bölüm
Lisans
Telif Hakkı (c) 2025 Black Sea Journal of Artificial Intelligence
Bu çalışma Creative Commons Attribution-NonCommercial 4.0 International License ile lisanslanmıştır.
