人工智能赋能的《信息隐藏》课程教学创新探讨
Discussion on the Teaching Innovation of the “Information Hiding” Course Empowered by Artificial Intelligence
摘要: 随着人工智能技术的快速发展，大语言模型在教育教学中的应用为课程改革提供了新的思路与工具。《信息隐藏》作为网络空间安全学科的重要课程，长期以来在教学中存在理论抽象、实践资源有限、个性化不足等痛点。本文基于人工智能赋能的视角，系统探讨了《信息隐藏》课程的教学创新路径。具体包括：通过智能化教学辅助工具实现实验错误定位与反馈优化；基于学习数据的个性化学习支持与资源推荐；依托跨学科案例推动实验与实践教学创新；构建多维度的课程评价体系以实现持续改进。研究结果表明，人工智能的引入不仅能够提升学生对复杂概念的理解与掌握，还能有效缓解教师的教学压力，促进科研与教学的深度融合。最后，本文提出了课程未来的优化方向，包括技术局限突破、数据隐私保护、师资培训与跨学科融合等，为网络空间安全学科人才培养提供参考。
Abstract: With the rapid development of artificial intelligence technologies, the application of large language models in education provides new perspectives and tools for curriculum reform. Information Hiding, as a core course in the discipline of Cyberspace Security, has long faced challenges such as abstract theoretical concepts, limited practical resources, and insufficient personalized support. This paper explores innovative teaching approaches for the Information Hiding course from the perspective of AI empowerment. Specifically, it introduces intelligent teaching assistants for error diagnosis and feedback optimization, personalized learning support and resource recommendation based on learning data, cross-disciplinary case integration for experimental innovation, and a multidimensional evaluation system for continuous improvement. The study shows that the integration of AI not only enhances students’ comprehension of complex concepts but also alleviates teachers’ workload and fosters deeper synergy between research and teaching. Finally, the paper discusses future optimization directions, including overcoming technical limitations, ensuring data privacy, enhancing faculty training, and promoting cross-disciplinary integration, providing useful insights for cultivating high-level talents in cyberspace security.
文章引用：冯丙文, 吴小天, 宋婷婷, 李佩雅, 耿光刚. 人工智能赋能的《信息隐藏》课程教学创新探讨[J]. 教育进展, 2025, 15(10): 848-861. https://doi.org/10.12677/ae.2025.15101910

参考文献

[1] Zhu, J., Kaplan, R., Johnson, J. and Fei-Fei, L. (2018) HiDDeN: Hiding Data with Deep Networks. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Lecture Notes in Computer Science, Springer International Publishing, 682-697. [Google Scholar] [CrossRef] 
[2] Zhang, R., Dong, S. and Liu, J. (2019) Invisible Steganography via Generative Adversarial Networks. Multimedia Tools and Applications, 78, 8559-8575. [Google Scholar] [CrossRef] 
[3] Tancik, M., Mildenhall, B. and Ng, R. (2020) Stegastamp: Invisible Hyperlinks in Physical Photographs. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 2117-2126. [Google Scholar] [CrossRef] 
[4] Qian, Y., Dong, J., Wang, W. and Tan, T. (2015) Deep Learning for Steganalysis via Convolutional Neural Networks. Media Water-Marking, Security, and Forensics, 1-11.
[5] Wu, H., Zhou H, Zheng W, et al. (2024) A Comprehensive Survey on Image Steganalysis Using Deep Learning. Information Sciences, 674, Article 119574.
[6] Liu, Z., Xu, X., Qiao, P. and Li, D. (2025) Acceleration for Deep Reinforcement Learning Using Parallel and Distributed Computing: A Survey. ACM Computing Surveys, 57, 1-35. [Google Scholar] [CrossRef] 
[7] Yang, W., Wang, Y. and Zhang, X. (2024) LLM-Stega: Generative Text Steganography with Large Language Models. arXiv:2403.12345.
[8] Fang, Y., Wang, X. and Li, Z. (2023) Neural Linguistic Steganography and Its Detection. IEEE Transactions on Information Forensics and Security, 18, 1123-1136.
[9] Yang, Y., Li, M. and Xu, J. (2024) Adversarial Attacks and Defenses in Text Steganography. Computers & Security, 139, Article 103615.
[10] Kirchenbauer, J., Geiping, J., Wen, Y., et al. (2023) A Watermark for Large Language Models. International Conference on Machine Learning.
[11] Zhao, Z., Bansal, M. and Durmus, E. (2023) On the Reliability of Watermarks for Large Language Models. The Twelfth International Conference on Learning Representations, 123-135.
[12] Roman, R.S., Fernandez, P., Elsahar, H., Défossez, A., Furon, T. and Tran, T. (2024) AudioSeal: Proactive Detection of Voice Cloning with Localized Watermarking. In: Forty-First International Conference on Machine Learning, ICML.
[13] NIST (2024) Reducing Risks Posed by Synthetic Content: NIST AI 100-4 Draft Report.
[14] Lin, J., Chen, Y. and Zhang, H. (2024) Deep Learning-Based Steganography Experiments in Cybersecurity Education. Proceedings of the 2024 IEEE Frontiers in Education Conference, Urbana, IL, 23-26 October 2024, 455-462.
[15] Lee, D. and Park, J. (2023) Teaching Steganalysis with Adversarial Examples in Undergraduate Security Courses. Proceedings of the ACM Conference on Computer Science Education, Toronto, 15-18 March 2023, 98-105.
[16] Zhang, K., Wu, Z. and Chen, T. (2019) SteganoGAN: High Capacity Image Steganography with GANs. ACM Multimedia Conference, Nice, 21-25 October 2019, 75-83.
[17] Li, H., Sun, Z. and Liu, X. (2024) Teaching Digital Watermarking with AI-Generated Content Cases. Journal of Information Security Education, 15, 35-47.
[18] Chen, W. and Zhao, X. (2025) Curriculum Design for AI Watermarking and Content Provenance in Cyberspace Security Programs. Computers & Security, 142, Article 103811.
[19] Wang, Y. and Zhao, Q. (2025) Personalized Learning Support for Information Hiding Courses with Large Language Models. Proceedings of the 2025 International Conference on Advanced Learning Technologies, Paris, 30-31 October 2025, 250-258.
[20] Xu, J., He, Y. and Zhang, P. (2025) Integrating Ethics and Legal Aspects into AI-Powered Steganography Teaching. ACM Transactions on Computing Education, 25, 1-20. [Google Scholar] [CrossRef] 

为你推荐