人工智能技术在网络安全评估中的应用与影响综述
A Review of Artificial Intelligence Technology: Applications and Impacts in Cybersecurity Evaluation
摘要: 本文综述了人工智能技术在网络安全评估领域的应用现状。其核心应用涵盖漏洞检测与管理、入侵检测与防御、风险评估与态势感知等关键方向。在系统梳理各研究领域进展的基础上，详细阐释了人工智能技术在网络安全评估中所发挥的关键作用，包括显著提升检测精度与效率、具备强大的自适应学习能力，以及能够针对研究对象展开全面且深入的分析等。然而，人工智能在网络安全评估实践中仍面临多重挑战：高质量标注数据短缺与隐私泄露风险、模型可解释性不足，以及抗攻击能力薄弱。基于上述现状，本文梳理了人工智能与人协同工作的现有实践模式，总结了联邦学习在网络安全领域的应用进展与拓展潜力，并探讨了量子计算环境下网络安全评估方法的变革趋势。期望通过以上分析，为读者全方位呈现人工智能在网络安全评价中的应用图景，同时为后续相关研究提供参考。
Abstract: This paper provides a comprehensive review of the application status of artificial intelligence technology in the field of cybersecurity assessment. Its core applications cover key directions such as vulnerability detection and management, intrusion detection and prevention, as well as risk assessment and situational awareness. Based on a systematic collation of research progress across various fields, this paper elaborates on the pivotal roles played by AI technology in cybersecurity assessment, including significantly improving detection accuracy and efficiency, possessing robust adaptive learning capabilities, and enabling comprehensive and in-depth analysis of assessment objects. However, AI still faces multiple challenges in practical cybersecurity assessment: the shortage of high-quality labeled data, risks of privacy leakage, insufficient model interpretability, and weak adversarial attack resistance. In light of the aforementioned status quo, this paper summarizes the existing practical models of human-AI collaborative work, synthesizes the application progress and expansion potential of federated learning in the cybersecurity domain, and discusses the evolutionary trends of cybersecurity assessment methodologies in the quantum computing era. It is anticipated that through the aforementioned analysis, this paper will comprehensively present the application landscape of AI in cybersecurity assessment and provide references for subsequent related research.
文章引用：范佳誉. 人工智能技术在网络安全评估中的应用与影响综述[J]. 人工智能与机器人研究, 2026, 15(2): 411-419. https://doi.org/10.12677/airr.2026.152040

参考文献

[1] Arreche, O. and Abdallah, M. (2024) A Comparative Analysis of DNN-Based White-Box Explainable AI Methods in Network Security.
https://arxiv.org/abs/2501.07801
[2] Ren, H., Lan, X., Tang, R. and Chen, X. (2025) PrivDNFIS: Privacy-Preserving and Efficient Deep Neuro-Fuzzy Inference System. Proceedings of the AAAI Conference on Artificial Intelligence, 39, 20174-20182. [Google Scholar] [CrossRef] 
[3] 陈朗, 王春玲. 基于机器学习的Android系统漏洞扫描处理系统设计[J]. 电脑知识与技术, 2019, 15(25): 20-22.
[4] 张锦蓉, 刘伟民. 基于漏洞扫描的网络安全维护策略探讨[J]. 信息与电脑(理论版), 2024, 36(22): 89-91.
[5] 曹文, 胡志锋, 代飞. 基于Python的通信网络安全漏洞扫描技术研究与实现[J]. 电脑编程技巧与维护, 2024(11): 171-173.
[6] Lacombe, G. and Sébastien, B. (2025) Attacker Control and Bug Prioritization.
https://arxiv.org/abs/2501.17740
[7] Zeng, Z., Huang, D., Xue, G., Deng, Y., Vadnere, N. and Xie, L. (2024) ILLATION: Improving Vulnerability Risk Prioritization by Learning from Network. IEEE Transactions on Dependable and Secure Computing, 21, 1890-1901. [Google Scholar] [CrossRef] 
[8] Jiang, Y., Oo, N., Meng, Q., et al. (2025) A Survey on Vulnerability Prioritization: Taxonomy, Metrics, and Research Challenges.
https://arxiv.org/abs/2502.11070
[9] 尹梓诺, 陈鸿昶, 马海龙, 等. 无监督自适应抽样与改进孪生网络结合的网络流量异常检测方法[J]. 电子与信息学报, 2025, 47(7): 2211-2224.
[10] 池彬, 胡辉, 周天宇, 等. 一种改进自编码器与流特征结合的入侵检测方法[J]. 重庆理工大学学报(自然科学), 2025, 39(7): 119-126.
[11] 史承斌. 基于深度学习的网络入侵检测与防御机制[J]. 无线互联科技, 2024, 21(14): 123-125.
[12] 陈智勇. 基于深度学习的网络入侵检测与防御研究[J]. 无线互联科技, 2023, 20(19): 152-154.
[13] 廖天颖, 杨斯博, 窦润亮. 基于贝叶斯网络的大数据安全动态风险评估模型研究[J]. 网络空间安全, 2023, 14(1): 60-68.
[14] 张小雷. 基于态势感知的高校网络安全实践探索[J]. 网络安全技术与应用, 2024(11): 64-66.
[15] 施雪清. 基于人工智能技术的计算机网络安全风险评估系统设计[J]. 信息与电脑(理论版), 2023, 35(23): 199-202.
[16] 亓文法. 基于人工智能的网络安全态势评估技术综述及展望[J]. 保密科学技术, 2024(10): 42-48.
[17] 王书义. 人工智能驱动的网络安全威胁检测与防御策略[J]. 信息记录材料, 2025, 26(8): 40-42.
[18] Goldschmidt, P. and Chudá, D. (2025) Network Intrusion Datasets: A Survey, Limitations, and Recommendations.
https://arxiv.org/abs/2502.06688
[19] 韩凤董, 宗学军, 何戡, 等. 面向网络安全不平衡数据的特征学习和分类研究应用[J]. 科学技术与工程, 2023, 23(3): 1130-1137.
[20] Du, M., Li, F., Zheng, G. and Srikumar, V. (2017) DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, 30 October-3 November 2017, 1285-1298. [Google Scholar] [CrossRef] 
[21] Chen, H. and Babar, M.A. (2024) Security for Machine Learning-Based Software Systems: A Survey of Threats, Practices, and Challenges. ACM Computing Surveys, 56, 1-38. [Google Scholar] [CrossRef] 
[22] 王子帆. 基于梯度反演的模型隐私攻击及防御方法研究[D]: [硕士学位论文]. 贵阳: 贵州大学, 2023.
[23] 周炜, 王超, 徐剑, 胡克勇, 王金龙. 基于区块链的隐私保护去中心化联邦学习模型[J]. 计算机研究与发展, 2022, 59(11): 2423-2436.
[24] Hu, W. and Fang, H. (2024) Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach. ACM Transactions on Knowledge Discovery from Data, 18, 1-21. [Google Scholar] [CrossRef] 
[25] Kairouz, P. and McMahan, H.B. (2021) Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning, 14, 1-210. [Google Scholar] [CrossRef] 
[26] Weng, J., Weng, J., Zhang, J., et al. (2021) DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-Based Incentive. IEEE Transactions on Dependable and Secure Computing, 18, 2568-2582.
[27] Nasr, M., Songi, S., Thakurta, A., Papernot, N. and Carlin, N. (2021) Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. 2021 IEEE Symposium on Security and Privacy (SP), San Francisco, 24-27 May 2021, 866-882. [Google Scholar] [CrossRef] 
[28] Mora, A., Tenison, I., Bellavista, P., et al. (2022) Knowledge Distillation for Federated Learning: A Practical Guide.
https://arxiv.org/abs/2211.04742
[29] Fatema, K., Anannya, M., Dey, S.K., Su, C. and Mazumder, R. (2024) Securing Networks: A Deep Learning Approach with Explainable AI (XAI) and Federated Learning for Intrusion Detection. In: Lecture Notes in Computer Science, Springer, 260-275. [Google Scholar] [CrossRef] 
[30] Brosolo, M., Puthuvath, V. and Conti, M. (2025) The Road Less Traveled: Investigating Robustness and Explainability in CNN Malware Detection.
https://arxiv.org/abs/2503.01391
[31] 马春来, 王群, 孙中豪, 等. 基于人机协作迭代分析的网络协议逆向方法[J]. 信息对抗技术, 2024, 3(5): 84-96.
[32] Singh, N. (2025) Enhancing Search and Discovery: The Synergistic Collaboration between Humans and AI. European Journal of Computer Science and Information Technology, 13, 112-123. [Google Scholar] [CrossRef] 
[33] Arker, I.H., Janicke, H., Mohammad, N., et al. (2023) AI Potentiality and Awareness: A Position Paper from the Perspective of Human-AI Teaming in Cybersecurity.
https://arxiv.org/abs/2310.12162
[34] Mcmahan, H.B., Moore, E., Ramage, D., et al. (2016) Communication-Efficient Learning of Deep Networks from Decentralized Data.
https://arxiv.org/abs/1602.05629
[35] Pachar, S., Dhabhai, A., Vali, S.M., Sharma, D., Yadav, S. and Khatoon, A. (2024) A Survey of Federated Learning for Internet of Things: Recent Advances, Research Problems and Solutions. 2024 International Conference on Augmented Reality, Intelligent Systems, and Industrial Automation (ARIIA), Manipal, 20-21 December 2024, 1-4.
[36] 康海燕, 张聪明. 基于联邦学习的自适应网络攻击分析方法研究[J]. 信息安全研究, 2024, 10(12): 1091-1099.
[37] Jiang, Y., Ma, B., Wang, X., et al. (2023) A Secure Aggregation for Federated Learning on Long-Tailed Data.
https://arxiv.org/abs/2307.08324
[38] 余锋, 林庆新, 林晖, 等. 基于生成对抗网络的隐私增强联邦学习方案[J]. 网络与信息安全学报, 2023, 9(3): 113-122.
[39] Li, Z., Lin, T., Shang, X., et al. (2023) Revisiting Weighted Aggregation in Federated Learning with Neural Networks.
https://arxiv.org/abs/2302.10911
[40] Preskill, J. (2018) Quantum Computing in the NISQ Era and beyond. Quantum, 2, Article 79. [Google Scholar] [CrossRef] 
[41] 王宝楠, 胡风, 张焕国, 等. 从演化密码到量子人工智能密码综述[J]. 计算机研究与发展, 2019, 56(10): 2112-2134.
[42] 张梓钧. 量子通信对现代电信网络安全的影响分析[J]. 集成电路应用, 2025, 42(1): 126-127.
[43] 张燕. 量子技术在通信网络安全方面的应用[J]. 电气自动化, 2022, 44(2): 72-74+77.
[44] Havlíček, V., Córcoles, A.D., Temme, K., Harrow, A.W., Kandala, A., Chow, J.M., et al. (2019) Supervised Learning with Quantum-Enhanced Feature Spaces. Nature, 567, 209-212. [Google Scholar] [CrossRef] [PubMed]

为你推荐