基于LLM的跨架构物联网静态漏洞挖掘检测 参考文献

最新推荐文章于 2025-09-04 22:11:39 发布
原创 最新推荐文章于 2025-09-04 22:11:39 发布 · 521 阅读 · 16 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#网络安全 #LLM #人工智能 #物联网 #IEEE #ACM #顶会

References:

  1. Y.Zhang, J.T.Li, X.Y.Song, et al. “Overview of IoT device security detection”(in Chinese),  Computer Research and Development, 2023, 60 (10): 2271-2290.
  2. K.KELLY. “The Ring Video Doorbell and the Entry of Amazon into the Smart Home: Implications for Consumer-Initiated Surveillance”, Journal of Consumer Policy, 2023, 46(1): 95-104.
  3. S. M. Sajjad, M. Yousaf, H. Afzal, et al. "eMUD: Enhanced Manufacturer Usage Description for IoT Botnets Prevention on Home WiFi Routers," in IEEE Access, vol. 8, pp. 164200-164213, 2020, doi: 10.1109/ACCESS.2020.3022272.
  4. D.A.Tanner, A.Hinchliffe, D.Santos. Threat assessment: Blackcat ransomware [EB/OL]. (2022-01-27) [2023-08-25]. https://unit42.Paloaltonetworks.com/blackcatransomware/
  5. D.BONAVENTURA, S.ESPOSITO, G.BELLA. Smart bulbs can be hacked to hack into your household arXiv preprint arXiv:2308.09019 (2023).
  6. Jason Wei, Yi Tay, Rishi Bommasani, et al.Emergent abilities of large language models [EB/OL］. [2023-03-10]. https://arxiv. org/pdf/2206.07682.pdf.
  7. Vaswani A，Shazeer N，Parmar N，et al．Attention is all you need[C]//Advances in Neural Information Processing Systems 30：Annual Conf on Neural Information Processing Systems 2017 New York：Curran Associates，2017：5998 6008.
  8. Emily M. Bender, Timnit Gebru, Angelina McMillan-Major, et al.On the dangers of stochastic parrots：Can language models be too big?[C]//Proc of the 2021 ACM Conf on Fairness，Accountability，and Transparency.New York:ACM，2021:610 623.
  9. GOERTZEL B. Artificial general intelligence：concept, state of the art, and future prospects[J].Journal of Artificial General Intelligence,2014,5(1):1-46.
  10. Alex Tamkin, Miles Brundage, Jack Clark, et al．Understanding the capabilities，limitations，and societal impact of large language models[J]arXiv preprint,arXiv:2102.02503,2021.
  11. Michael Fu, Chakkrit Tantithamthavorn. Linevul: a transformer-based linelevel vulnerability prediction. In Proceedings of the 19th International Conference on Mining Software Repositories, pages 608–620, 2022.
  12. Van-Anh Nguyen, Dai Quoc Nguyen, Van Nguyen, et al. Regvd: Revisiting graph neural networks for vulnerability detection. In Proceedings of the ACM/IEEE 44th International Conference on Software Engineering: Companion Proceedings, pages 178–182, 2022.
  13. Yiran Cheng, Lwin Khin Shar, Ting Zhang, et al. LLM-Enhanced Static Analysis for Precise Identification of Vulnerable OSS Versions[J]. arXiv preprint arXiv:2408.07321, 2024.
  14. W. M. Khoo, A. Mycroft, R. Anderson. Rendezvous: A search engine for binary code. In Proceedings of the 10th Working Conference on Mining Software Repositories, 2013.
  15. H. Flake. Structural comparison of executable objects. In DIMVA, volume 46, 2004.
  16. J. Pewny, B. Garmany, R. Gawlik, et al. Cross-Architecture Bug Search in Binary Executables[C]. IEEE Symposium on Security and Privacy, 2015.
  17. Eschweiler S, Yakdan K, Gerhards-Padilla E. discovRE: Efficient Cross-Architecture Identification of Bugs in Binary Code[J].  2016.DOI:10.14722/ndss.2016.23185.
  18. Feng Q, Zhou R, Xu C, et al. Scalable Graph-based Bug Search for Firmware Images[C]//Acm Sigsac Conference on Computer & Communications Security.ACM, 2016.DOI:10.1145/2976749.2978370.
  19. Franco Scarselli, Marco Gori, Ah Chung Tsoi, et al. 2009. The graph neural network model. IEEE Transactions on Neural Networks 20, 1 (2009), 61–80.
  20. Hanjun Dai, Bo Dai, Le Song. 2016. Discriminative Embeddings of Latent Variable Models for Structured Data. In International Conference on Machine Learning.
  21. Ding S H H, Fung B C M, Charland P. Asm2Vec: Boosting Static Representation Robustness for Binary Clone Search against Code Obfuscation and Compiler Optimization[J]. IEEE Computer Society, 2019, 10(1109): 472-489.
  22. X. Xu, C. Liu, Q. Feng, et al. “Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection,” in Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. Dallas Texas USA: ACM, Oct. 2017, pp. 363–376. [Online]. Available: https://dl.acm.org/doi/10.1145/3133956.3134018
  23. Yujia Li，Chenjie Gu，Thomas Dullien，et al. Graph Matching Networks for Learning the Similarity of Graph Structured Objects[J]. International Conference on Machine Learning, 2019, 10(48550): 1904-12787.
  24. V. Cochard, D. Pfammatter, C. T. Duong, et al. "Investigating Graph Embedding Methods for Cross-Platform Binary Code Similarity Detection," 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P), Genoa, Italy, 2022, pp. 60-73, doi: 10.1109/EuroSP53844.2022.00012.
  25. Benjamin Steenhoek, Md Mahbubur Rahman, Richard Jiles, et al. An empirical study of deep learning models for vulnerability detection[C]//2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2023: 2237-2248.
  26. Wang J, Yu L, Luo X. Llmif: Augmented large language model for fuzzing iot devices[C]//2024 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 2024: 196-196.
  27. Zhou X, Cao S, Sun X, et al. Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead[J]. 2024.
  28. Weng C, Qin Y, Lin B, et al. Matsvd: Boosting statement-level vulnerability detection via dependency-based attention[C]//Proceedings of the 15th Asia-Pacific Symposium on Internetware. 2024: 115-124.
  29. Yang X, Wang S, Li Y, et al. Does data sampling improve deep learning-based vulnerability detection? Yeas! and Nays![C]//2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2023: 2287-2298.
  30. Ding Y, Fu Y, Ibrahim O, et al. Vulnerability detection with code language models: How far are we?[J]. arXiv preprint arXiv:2403.18624, 2024.
  31. Wen X C, Wang X, Gao C, et al. When less is enough: Positive and unlabeled learning model for vulnerability detection[C]//2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE). IEEE, 2023: 345-357.
  32. Kuang H, Yang F, Zhang L, et al. Leveraging user-defined identifiers for counterfactual data generation in source code vulnerability detection[C]//2023 IEEE 23rd International Working Conference on Source Code Analysis and Manipulation (SCAM). IEEE, 2023: 143-150.
  33. Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 2019: 4171-4186.
  34. Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners[J]. OpenAI blog, 2019, 1(8): 9.
  35. Liu Z, Tang Z, Zhang J, et al. Pre-training by predicting program dependencies for vulnerability analysis tasks[C]//Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 2024: 1-13.
  36. Peng T, Chen S, Zhu F, et al. PTLVD: Program Slicing and Transformer-based Line-level Vulnerability Detection System[C]//2023 IEEE 23rd International Working Conference on Source Code Analysis and Manipulation (SCAM). IEEE, 2023: 162-173.
  37. Wang H, Tang Z, Tan S H, et al. Combining structured static code information and dynamic symbolic traces for software vulnerability prediction[C]//Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 2024: 1-13.
  38. Zhang J, Liu Z, Hu X, et al. Vulnerability detection by learning from syntax-based execution paths of code[J]. IEEE Transactions on Software Engineering, 2023, 49(8): 4196-4212.
  39. Tran H C, Tran A D, Le K H. DetectVul: A statement-level code vulnerability detection for Python[J]. Future Generation Computer Systems, 2025, 163: 107504.
  40. Tang W, Tang M, Ban M, et al. CSGVD: A deep learning approach combining sequence and graph embedding for source code vulnerability detection[J]. Journal of Systems and Software, 2023, 199: 111623.
  41. Jiang Z, Sun W, Gu X, et al. DFEPT: data flow embedding for enhancing pre-trained model based vulnerability detection[C]//Proceedings of the 15th Asia-Pacific Symposium on Internetware. 2024: 95-104.
  42. Yang A Z H, Tian H, Ye H, et al. Security vulnerability detection with multitask self-instructed fine-tuning of large language models[J]. arXiv preprint arXiv:2406.05892, 2024.
  43. Ziems N, Wu S. Security vulnerability detection using deep learning natural language processing[C]//IEEE INFOCOM 2021-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). IEEE, 2021: 1-6.
  44. Hanif H, Maffeis S. Vulberta: Simplified source code pre-training for vulnerability detection[C]//2022 International joint conference on neural networks (IJCNN). IEEE, 2022: 1-8.
  45. Liu Y, Ott M, Goyal N, et al. Roberta: A robustly optimized bert pretraining approach[J]. arXiv preprint arXiv:1907.11692, 2019.
  46. Ni C, Yin X, Yang K, et al. Distinguishing look-alike innocent and vulnerable code by subtle semantic representation learning and explanation[C]//Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2023: 1611-1622.
  47. Steenhoek B, Rahman M M, Sharmin S, et al. Do language models learn semantics of code? A case study in vulnerability detection[J]. arXiv preprint arXiv:2311.04109, 2023.
  48. Rahman M M, Ceka I, Mao C, et al. Towards causal deep learning for vulnerability detection[C]//Proceedings of the IEEE/ACM 46th international conference on software engineering. 2024: 1-11.
  49. Zhou X, Zhang T, Lo D. Large language model for vulnerability detection: Emerging results and future directions[C]//Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results. 2024: 47-51.
  50. Fu M, Tantithamthavorn C K, Nguyen V, et al. Chatgpt for vulnerability detection, classification, and repair: How far are we?[C]//2023 30th Asia-Pacific Software Engineering Conference (APSEC). IEEE, 2023: 632-636.
  51. Zhou X, Tran D M, Le-Cong T, et al. Comparison of static application security testing tools and large language models for repo-level vulnerability detection[J]. arXiv preprint arXiv:2407.16235, 2024.
  52. Yin X. Pros and cons! evaluating chatgpt on software vulnerability[J]. arXiv preprint arXiv:2404.03994, 2024.
  53. Khare A, Dutta S, Li Z, et al. Understanding the effectiveness of large language models in detecting security vulnerabilities[J]. arXiv preprint arXiv:2311.16169, 2023.
  54. Zhang C, Liu H, Zeng J, et al. Prompt-enhanced software vulnerability detection using ChatGPT (2024)[J]. arXiv preprint arXiv:2308.12697.
  55. Kojima T, Gu S S, Reid M, et al. Large language models are zero-shot reasoners[J]. Advances in neural information processing systems, 2022, 35: 22199-22213.
  56. Ni C, Shen L, Xu X, et al. Learning-based models for vulnerability detection: An extensive study[J]. arXiv preprint arXiv:2408.07526, 2024.
  57. Liu Z, Liao Q, Gu W, et al. Software vulnerability detection with gpt and in-context learning[C]//2023 8th International Conference on Data Science in Cyberspace (DSC). IEEE, 2023: 229-236.
  58. Du X, Zheng G, Wang K, et al. Vul-rag: Enhancing llm-based vulnerability detection via knowledge-level rag[J]. arXiv preprint arXiv:2406.11147, 2024.
  59. Wen X C, Wang X, Chen Y, et al. Vuleval: Towards repository-level evaluation of software vulnerability detection[J]. arXiv preprint arXiv:2404.15596, 2024
  60. Wang L, Ma C, Feng X, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.
  61. Qin Y, Liang S, Ye Y, et al. Toolllm: Facilitating large language models to master 16000+ real-world apis[J]. arXiv preprint arXiv:2307.16789, 2023.
  62. Shao Z, Gong Y, Shen Y, et al. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy[J]. arXiv preprint arXiv:2305.15294, 2023.
  63. Trivedi H, Balasubramanian N, Khot T, et al. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions[J]. arXiv preprint arXiv:2212.10509, 2022.
  64. Asai A, Wu Z, Wang Y, et al. Self-rag: Learning to retrieve, generate, and critique through self-reflection[C]//The Twelfth International Conference on Learning Representations. 2023.
  65. “National Security Governance in the Digital Age” (in Chinese), Legal Times, 2025, (04): 6.
  66. J.Ma, H.Yuan. "Network Attack on Asian Winter Games: 3 U.S. Agents Wanted" (in Chinese), Global Times, April 16, 2025, p. 008.
  67. D.Y.Su. “Strengthening Cybersecurity Barriers to Safeguard National Security” (in Chinese), People's Posts and Telecommunications, April 15, 2025, p. 001.
  68. Y.P.Lai, Y.N.Wei. "Exploring the Ideological and Political Construction Path of Information Security Courses in Universities from the Perspective of Patriotism Education" (in Chinese), Journal of Yunnan University (Social Sciences Edition), 2025, (02): 135-144. [Online] Available: https://doi.org/10.19833/j.cnki.jyu.2025.02.003 (Accessed April 28, 2025).
  69. X.A.Zhong. "Elevating Vulnerability Governance to the National Security Level for Unified Deployment" (in Chinese), China Information Security, 2024, (05): 5.
  70. M.Cao, W.Ren. "Adhering to the Holistic National Security Concept: Accelerating Cybersecurity Vulnerability Governance to Empower New Quality Productive Forces Development" (in Chinese), China Information Security, 2024, (05): 20-22.
  71. Z.Xin, L.L.Hao, C.J.Hou, et al., "Cultivation Strategies for College Students' National Security Literacy in the Age of AI" (in Chinese), Journal of Electrical and Electronic Education, 2025, (01): 87-90.
  72. Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint arXiv:1312.6199, 2013.
  73. Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples[J]. arXiv preprint arXiv:1412.6572, 2014.

附中文参考文献:

[1]    张妍,黎家通,宋小祎,等. 物联网设备安全检测综述[J]. 计算机研究与发展,2023,60(10):2271-2290. DOI:10.7544/issn1000-1239.202330482.

大模型时代的软件架构设计
AI天才研究院
11-14 1057
本文系统地探讨了大模型时代的软件架构设计。首先，我们介绍了大模型时代的背景与意义，分析了大模型在软件架构设计中的核心地位。接着，我们深入讲解了神经网络与深度学习基础，以及大模型训练方法与优化算法。然后，本文详细探讨了大模型在数据处理与存储、实时计算与推理、分布式系统架构中的应用。此外，我们还分析了大模型时代的安全挑战，并提出了相应的安全保护技术和最佳实践。最后，本文介绍了大模型时代的技术栈与工具集，并展望了大模型在医疗健康、金融和工业自动化等领域的应用前景。
DeepSeek 赋能智能教育知识图谱：从构建到应用的革命性突破
邓邓子的博客
06-07 1242
随着教育智能化发展，智能教育知识图谱成为教育变革的关键技术。本文聚焦 DeepSeek 在智能教育知识图谱构建与应用中的实践，深入探讨其技术特性与应用价值。DeepSeek 凭借强大的自然语言处理、多模态交互和数据分析能力，在知识图谱数据处理、语义关系挖掘、本体构建等环节发挥核心作用。同时，在个性化学习支持、智能教学辅助、教育管理优化等多场景实现创新应用。通过典型案例分析，展示其显著成效。文章也剖析了当前面临的挑战，并对 DeepSeek 在智能教育领域的未来发展进行展望，为教育智能化研究与实践提供参考。
基于LLM的跨架构物联网静态漏洞挖掘检测 前言
XLYcmy的博客
08-23 531
2022年12月，哥伦比亚最大的公共能源、水源和天然气供应商之一Empresas Publicas de Medellin（EPM）的IoT系统也未能幸免于难，遭受了黑猫勒索软件的攻击，此次攻击导致公司的计算机基础设施瘫痪，在线服务中断，对大量用户造成了严重的影响[4]；随着物联网（Internet of Things，IoT）的日益发展，物联网设备已经深深地渗透到我们日常生活的方方面面，无论是家庭中冰箱、电视的一次次智能化升级，还是城市中随处可见的照明设备和智能传感器等等，都昭示着物联网的广泛覆盖。
基于LLM的跨架构物联网静态漏洞挖掘检测 研究考虑
XLYcmy的博客
08-27 493
NVD成为全球安全预警和漏洞发布的重要平台，在网络安全漏洞的发现收集、验证评估、修复消控、披露和跟踪上建立了较完备的漏洞治理体系，领先优势显著。然而，仍存在许多不足。三是要构建起数字安全防御体系，并发展能投入实战应用的安全大模型，大幅度提升技术人员的安全分析、安全处置、应急响应、安全运营能力等。根据《2024年网络安全产业人才发展报告》显示，截至2024年6月，我国已有626所高校开设网络空间安全专业，其中283所本科院校，343所高职院校，网络安全专业占全国高等院校总数的1/5以上[68]。
基于LLM的跨架构物联网静态漏洞挖掘检测 前沿研究综述之结合LLM的漏洞检测技术
XLYcmy的博客
08-24 353
根据文献[27]的统计，目前对于应用LLM的静态漏洞检测技术主要包括三种：微调（约占73%）、prompt工程（约占17%）和检索增强（约占10%）。同时，基于LLM的漏洞检测研究所使用的数据集主要集中在函数级或行级输入上，对于类或仓库级的探索则相对有限。此外，当前的方法并不强调与开发者工作流的集成，或者开发者与基于LLM的模型之间的互动和协作。在本节中将会对过往的工作做一个总结和介绍，首先会对之前的基于学习的静态检测技术进行一个梳理，接着对于结合LLM的漏洞检测技术展开介绍。
【网安AIGC专题】46篇前沿代码大模型论文、24篇论文阅读笔记汇总
热门推荐
定期分享我的发现和想法，感谢你的陪伴和支持
11-27 2万+
本文为邹德清教授的《网络安全专题》课堂笔记系列的文章，本次专题主题为大模型。 本系列文章不仅涵盖了46篇关于前沿代码大模型的论文，还包含了24篇深度论文阅读笔记，全面覆盖了代码生成、漏洞检测、程序修复、生成测试等多个应用方向，深刻展示了这些技术如何在网络安全领域中起到革命性作用。同时，本系列还细致地介绍了大模型技术的基础架构、增强策略、关键数据集，以及与网络安全紧密相关的模型安全问题。 本篇博客旨在整理这些宝贵的笔记，方便未来的阅读和研究，同时也希望能够对广大读者产生启发和帮助。让我们一起踏上这场网络安
LLMs之FT：《The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review o
头部AI社区如有邀博主AI主题演讲请私信—心比天高，仗剑走天涯，保持热爱，奔赴向梦想！低调，专注，谦虚，自律，反思，成长，还算比较正能量的博主，公益免费传播…内心特别想在AI界做出一些可以推进历史进程影响力的技术(兴趣使然，有点小情怀，也有点使命感呀
12-17 3362
​ LLMs：《The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities》翻译与解读
如何评价 DeepSeek v3 3月24日更新？
cxsde的博客
03-30 1384
根据国外开源评测平台kcores-llm-arena的最新测试数据，V3-0324的代码能力达到了328.3分，超过了普通版的Claude 3.7 Sonnet（322.3分），接近思维链版本的334.8分。同时，开源社区中的开发者也在积极参与模型的优化和改进，通过分享代码和经验，共同推动DeepSeek - V3 - 0324生态的发展。尽管面临着一些挑战，但通过不断的技术创新和社会各界的共同努力，它有望在未来发挥更大的作用，为人工智能的发展和社会的进步做出更大的贡献。
使用攻击知识图谱改进 ML-NIDS的泛化
hao_wujing的专栏
06-25 851
大家读完觉得有帮助记得关注和点赞！！！尽管对基于机器学习的网络入侵检测系统 （ML-NIDS） 进行了广泛研究，但它们检测各种攻击变体的能力仍不确定。以前的研究在很大程度上依赖于同质数据集，这些数据集人为地夸大了性能分数并提供虚假的安全感。设计能够有效检测各种攻击变体的系统仍然是一项重大挑战。ML-NIDS 的进展仍然在很大程度上依赖于人类专业知识，这可能会将系统设计人员的主观判断嵌入到模型中，从而可能阻碍其在各种攻击类型中泛化的能力。为了解决这一差距，我们提出了 KnowML，这是一个知识引导的机器学习框
一文解读，网络安全行业人才需求情况《网络安全产业人才发展报告》
weixin_59086772的博客
10-18 8764
随着近几天国家网络安全宣传周在全国各地开展活动，网络安全再一次成为热门话题。网络安全不再缩在小小的安全圈子里，惠及面越来越广。不少对网络安全颇有兴趣的朋友非常关心行业前景如何？该怎么提升自我能力，更快地加入网安行列。 今天雨笋君就10月13日在网络安全宣传周上发布的《2021网络安全人才报告》进行一个简单的行业前景分析。 一、网络安全行业市场发展情况 网络时代生活越来越离不开网络，与此同时发生的网络安全攻击事件、非法入侵等等一系列事件都威胁着普通人的生活。没有网络安全保障，个人和企业等重.
2025年09月03日最热门的开源项目(Github)
最新发布
09-04 306
模型常见训练超参数介绍(1)
my java博客园
09-02 1473
【摘要】本文总结了BERT/RoBERTa模型调参的关键策略：1）训练轮数需平衡过拟合与欠拟合，NER任务通常10+轮，分类任务3-5轮，推荐使用早停机制；2）学习率建议2e-5~5e-5，过高易震荡，过低收敛慢；3）batch size需适配显存，大batch需配合高学习率；4）warmup steps设为总步数5-20%，稳定训练初期；5）weight decay建议0.01-0.1，防止过拟合。调参时应监控训练/验证损失曲线，结合任务复杂度动态调整参数组合。（149字）
机器学习基础-day03-机器学习中的线性回归
XZSSWJS的博客
09-04 595
初学小小白，个人笔记使用，仅供参考
机器学习从入门到精通 - 强化学习初探：Q-Learning到Deep Q-Network实战
THMAIL的博客
09-04 1029
本文介绍了强化学习从Q-Learning到Deep Q-Network(DQN)的进阶过程。首先阐述了强化学习的基本框架，包括Agent、Environment、State、Action和Reward的交互关系，以及马尔可夫决策过程(MDP)的核心假设。重点讲解了Q-Learning算法，详细推导了其基于贝尔曼方程的时间差分更新公式，并说明了ε-greedy策略在探索与利用之间的平衡作用。随后指出Q-Table在处理高维状态空间时的局限性，进而引入DQN解决方案。DQN采用神经网络作为函数逼近器，并依靠经验
SpringAI Alibaba Graph 流式对话
weixin_60523038的博客
09-03 386
SrpingAi Alibaba Graph实现流式对话，工作流，Graph工作流，代码工作流，流式
扩散模型原理详解：从随机噪声到图像生成的数学逻辑
GEO_geo的博客
09-02 227
摘要：扩散模型是AI绘画（如Stable Diffusion）的核心技术，通过“噪声消除”生成图像。其核心分为正向扩散（逐步添加噪声使图像变为纯噪声）和逆向扩散（从噪声逐步去噪还原图像）。数学模型上，正向过程通过马尔可夫链描述噪声叠加，逆向过程则用U-Net预测噪声并迭代去噪。训练目标是最小化预测噪声与真实噪声的误差。扩散模型优势在于训练稳定、生成多样且细节丰富，通过数学建模与深度学习的结合，实现了“从混沌中创造秩序”的AI生成能力。
2024 Java AI实战：从机器学习到深度学习
keny-大成的博客
08-31 869
本文介绍了2024年Java在AI领域的应用实例，涵盖机器学习、NLP和计算机视觉等技术方向。主要内容包括：1）使用Deeplearning4j、TensorFlow等框架实现图像分类、线性回归等任务；2）基于OpenNLP、Stanford CoreNLP的NLP应用；3）计算机视觉案例；4）强化学习实现；5）Weka聚类分析；6）完整技术栈组合示例。特别提供了30个Tribuo文本分类代码框架，展示从数据加载到模型部署的全流程。文章还详细介绍了Weka聚类分析的Java实现方法，包括数据加载、算法选择和
AI-调查研究-69-具身智能 关键能力全景解析：算法、硬件、仿真与数据的系统综述
永远好奇，无限进步！
09-04 961
具身智能的发展依赖算法、硬件、仿真环境、嵌入式系统和数据处理的全方位支撑。智能算法是核心大脑，涵盖感知、认知和控制三层：感知侧通过视觉、听觉和多模态融合实现环境理解；认知层借助规划、强化学习与符号推理完成决策；控制层则确保精确动作执行，并结合端到端学习与混合智能架构优化性能。硬件作为“躯体”，包括高精度传感器、伺服驱动和异构计算平台，其性能直接决定智能水平。仿真环境提供安全高效的“数字训练场”，显著降低现实试错成本，支持大规模并行训练。嵌入式系统则构建从终端到云端的分层协同架构，保障实时性与稳定性。
Dify 从入门到精通（第 70/100 篇）：Dify 的多模态应用开发（高级篇）
haolove527的专栏
09-02 1525
Dify 的多模态应用开发是指在 Dify 平台上整合文本、图像和语音等多种模态数据，构建支持多模态输入和输出的应用，如结合文本问答、图像识别和语音交互的客服机器人、支持多模态搜索的知识库系统等。多模态应用通过预训练多模态模型（如 LLaVA、CLIP）或多模型组合（LLM + Whisper）实现，支持多语言（参考第六十三篇）和高可用性（参考第六十七篇）。
基于LLM的图异常检测
07-18
我们正在讨论基于大语言模型（LLM）的图结构异常检测方法与实现。图结构数据通常包含节点（实体）和边（关系），异常可能表现为节点、边或子图的异常模式。LLM因其强大的自然语言处理和理解能力，可以用于处理图结构...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值