互联网内容安全关键技术研究综述

摘要/Abstract

摘要： 随着互联网技术的飞速发展和内容创作分享的低门槛化，互联网内容安全成为当下互联网建设和监管的重点.以文本、图像、音频、视频为载体的信息内容剧增，给互联网内容安全带来巨大挑战.互联网内容安全内涵丰富，从多媒体内容过滤分析、信息伪造检测、舆情态势感知和数据保护4个方面对其中关键的技术进行介绍.同时，梳理实际应用中广泛采用的关键技术和相关研究工作.最后对互联网内容安全研究的关键问题进行探讨与展望.

关键词: 互联网内容安全, 多媒体内容过滤, 信息伪造检测, 舆情感知, 数据保护

Abstract: The rapid development of the Internet and easy content creation and sharing have made Internet content security a top priority for Internet construction and supervision. The dramatic increase of information content with text, image, audio, and video as carriers has brought great challenges to Internet content security. Internet content security is rich in connotation, and we focused on four key applications including multimedia content filtering, fake information detection, public opinion perception, and data protection. Then, we summarized key technologies and main research work adopted in those applications. Finally, we discussed and prospected key issues of Internet content security in future research.

Key words: Internet Content Security, Multimedia Content Filtering, Fake Information Detection, Public Opinion Perception, data protection

中图分类号:

TP393

廖忠, 王志昂, 申宇, 魏子令, 陈曙晖, . 互联网内容安全关键技术研究综述[J]. 信息安全研究, 2024, 10(3): 248-.

参考文献

［1］朱世强, 王永恒. 基于人工智能的内容安全发展战略研究［J］. 中国工程科学, 2021, 23(3): 6774［2］虎嵩林. 人工智能时代的内容安全服务. 信息安全研究［J］. 2019, 5(11): 959960［3］Sahami M, Dumais S, Heckerman D, et al. A bayesian approach to filtering junk email［C］ Proc of the Workshop of AAAI. Menlo Park, CA: AAAI, 1998: 98105［4］Drucker H, Wu D, Vapnik V N. Support vector machines for spam categorization［J］. IEEE Trans on Neural Networks, 1999, 10(5): 10481054［5］Yang Y, Liu X. A reexamination of text categorization methods［C］ Proc of the 22nd Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 1999: 4249［6］Hochreiter S, Schmidhuber J. Long shortterm memory［J］. Neural Computation, 1997, 9(8): 17351780［7］Kim Y. Convolutional neural networks for sentence classification［C］ Proc of the 2014 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014: 17461751［8］Yang Y, Lei Z, Zhang J W, et al. TICNN: Convolutional neural networks for fake news detection［J］. arXiv preprint, arXiv:1806.00749, 2018［9］Oord A V D, Dieleman S, Schrauwen B. Deep contentbased music recommendation［C］ Proc of the 26th Int Conf on Neural Information Processing Systems. New York: ACM, 2013: 26432651［10］Jin X, Wang Y, Tan X. Pornographic image recognition via weighted multiple instance learning［J］. IEEE Trans on Cybernetics, 2018, 49(12): 44124420［11］Yousaf K, Nawaz T. A deep learningbased approach for inappropriate content detection and classification of youtube videos［J］. IEEE Access, 2022, 10: 1628316298［12］Alguliyev R M, Abdullayeva F J, Ojagverdiyeva S S. Imagebasedmalicious internet content filtering method for child protection［J］. Journal of Information Security and Applications, 2022, 65:103123［13］Surameery N M S, Shakor M Y. Use chatgpt to solve programming bugs［J］. International Journal of Information Technology & Computer Engineering, 2023, 3(1): 1722［14］Ramesh A, Dhariwal P, Nichol A, et al. Hierarchical textconditional image generation with CLIP latents［J］. arXiv preprint, arXiv:2204.06125, 2022［15］中国信通院, 京东探索研究院. 人工智能生产内容(AIGC)白皮书［EBOL］. 2022 ［20230312］. http:www.caict.ac.cnsytj202209t20220913_408835.htm［16］Zhang H, Goodfellow I, Metaxas I, et al. Selfattention generative adversarial networks［J］. arXiv preprint, arXiv:1805.08318, 2018［17］Karras T, Laine S, Aila T. A stylebased generator architecture for generative adversarial networks［C］ Proc of the IEEECVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 44014410［18］Saha, S S, Singh A K, Bora P K. DeepFake detection: A systematic literature review［J］. IEEE Access, 2022, 10: 2549425513［19］Habeeba M A S, Lijiya A, ChackoA M. Detection of deepfakes using visual artifacts and neural network classifier［J］. Innovations in Electrical and Electronic Engineering, 2020, 661: 411422［20］Koopman M, Rodriguez A M, Geradts Z. Detection of deepfake video manipulation［C］ Proc of the 20th Irish Machine Vision and Image Processing Conf. Irish: IPRCS, 2018: 14［21］Zhang Y, Li Y, Wang J, et al. Coherentadversarial deepfake video generation［J］. Signal Processing, 2022,188: 108790［22］Alvi M A, Khan A M, Razaq S, et al. Warning: Humans cannot reliably detect speech deepfakes［J］. arXiv preprint, arXiv:2301.07829, 2023［23］McCombs M E. Newsinfluence on our pictures of the world［M］ Media Effects: Advances in Theory and Research. London: Routledge Press, 2002: 118［24］Pang B, Lee L. Opinion mining and sentiment analysis［J］. Foundations and Trends in Information Retrieval, 2008, 2(12): 1135［25］Liu B, Hu M, Cheng J. Opinion observer: Analyzing and comparing opinions on the Web［C］ Proc of the 14th Int Conf on World Wide Web.Geneva, Switzerland: IW3C2, 2005: 342351［26］Wang Z, Ye X. Social media analytics for natural disaster management［J］. International Journal of Geographical Information Science, 2018, 32(1): 4972［27］Leskovec J, Huttenlocher D, Kleinberg J. Predicting positive and negative links in online social networks［C］ Proc of the 19th Int Conf on World Wide Web.Geneva, Switzerland: IW3C2, 2010: 641650［28］Rakshit P, Sarkar P, Ghosh D, et al. Sentiment analysis of twitter data using deep learning［C］ Proc of ICCDN. Berlin: Springer, 2022: 495501［29］Davidson T, Warmsley D, Macy M, et al. Automated hate speech detection and the problem of offensive language［C］ Proc of the Int AAAI Conf on Web and Social Media. Menlo Park, CA: AAAI, 2017: 512515［30］张琛, 马祥元, 周扬,等. 基于用户情感变化的新冠疫情舆情演变分析［J］. 地球信息科学学报, 2021, 23(2): 341350［31］刘忠宝, 秦权, 赵文娟. 微博环境下新冠肺炎疫情事件对网民情绪的影响分析［J］. 情报杂志, 2021, 40(2): 138145［32］Shor P W. Polynomialtime algorithms for prime factorization and discrete logarithms on a quantum computer［J］. SIAM Review, 1999, 41(2): 303332［33］Grover L K. A fast quantum mechanical algorithm for database search［C］ Proc of the 28th Annual ACM Symp on Theory of Computing. New York: ACM, 1996: 212219［34］Bennett C H, Brassard G. Quantum cryptography: Public key distribution and coin tossing［J］. Theoretical Computer Science, 2014, 560: 711［35］Mceliece R J. A publickey cryptosystem based on algebraic［J］. Deep Space Network Progress Report, 1978, 4244: 114116［36］Zhang L, Zheng Y, Kantola R. A review of homomorphic encryption and its applications［C］ Proc of the 9th EAI Int Conf on Mobile Multimedia Communications. Belgium: EAI, 2016: 97106［37］Abadi M, Andersen D G. Learning to protect communications with adversarial neural cryptography［J］. arXiv preprint, arXiv:1610.06918, 2016［38］Zhang X W, Zhang Y L, Luo G P, et al. Identitybased format preserving encryption of data desensitization program［C］ Proc of Int Conf on Computer Engineering and Application. Piscataway, NJ: IEEE, 2020: 104107［39］Wang D, Xue W H, Li L L, et al. Research on data desensitization and penetration of intranet and extranet based on access control［C］ Proc of the 2nd Int Symp on Computer Engineering and Intelligent Communications. Piscataway, NJ: IEEE, 2021: 198201［40］Dwork C. Differential privacy［C］ Proc of the 51st Annual IEEE Symp on Foundations of Computer Science. Piscataway, NJ: IEEE, 2006: 112［41］Abadi M, Chu A, Goodfellow I, et al. Deep learning with differential privacy［C］ Proc of the 2016 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2016: 308318［42］Goldwasser S, Micali S,Rackoff C. The knowledge complexity of interactive proof systems［J］. SIAM Journal on Computing, 1989, 18: 186208［43］Blum M, Feldman P, Micali S. Noninteractive zeroknowledge and its applications［C］ Proc of the 20th Annual ACM Symp on Theory of Computing. New York: ACM, 2019: 103112［44］BenOr M, Goldwasser S, Wigderson A. Completeness theorems for noncryptographic faulttolerant distributed computation［C］ Proc of the 20th Annual ACM Symp on Theory of Computing. New York: ACM, 1988: 110［45］Fiat A, Shamir A. How to prove yourself: practical solutions to identification and signature problems［C］ Proc of Conf on the Theory and Application of Cryptographic Techniques. Berlin: Springer, 1986: 186194［46］Wang Y, Mianjy P, Arora R. Robust learning for data poisoning attacks［C］ Proc of Int Conf on Machine Learning. Hawaii: IMLS, 2021: 1085910869［47］Liu B, Ding M, Shaham S, et al. When machine learning meets privacy: A survey and outlook［J］. ACM Computing Surveys, 2022, 54(2): 136

[1]	于卫欣, 李文广, . 面向应急管理系统的“密码安全一体化”数据保护实践探索[J]. 信息安全研究, 2023, 9(E1): 218-.
[2]	许皖秀, 左晓栋, . 云平台数据保护与内容审核义务关系分析[J]. 信息安全研究, 2022, 8(11): 1079-.
[3]	孙雨潇, 张清芳, 符婷, 李艳丽, . 欧洲的接触者追踪技术（DP3T）之隐私考量[J]. 信息安全研究, 2021, 7(9): 810-814.
[4]	王娜顾绵雪伍高飞张玉清曹春杰. 跨境数据流动的现状、分析与展望 [J]. 信息安全研究, 2021, 7(6): 488-495.
[5]	王若曦. 数据可携权的争议与制度反思[J]. 信息安全研究, 2021, 7(11): 1063-.
[6]	解彦曦张弛. 欧盟《通用数据保护条例》数据保护认证制度研究[J]. 信息安全研究, 2021, 7(11): 1071-.
[7]	梅秋丽龚自洪刘尚焱王妮娜. 区块链平台安全机制研究梅秋丽1[J]. 信息安全研究, 2020, 6(1): 25-36.
[8]	周娇. 面向CDP系统的视图盘构建方法[J]. 信息安全研究, 2019, 5(2): 157-161.
[9]	庞鹏飞韩文聪薛源于长富谢长达. 基于Android内核的图像视频数据保护技术[J]. 信息安全研究, 2018, 4(4): 342-351.
[10]	马蔚彦. 动态变换技术防御Struts2 S2-032 零日攻击研究[J]. 信息安全研究, 2016, 2(8): 747-753.