A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2025  > In Press, Accepted Manuscript
W. Zhou, X. Zhu, Q.-L. Han, L. Li, X. Chen, S. Wen, and Y. Xiang, “The security of using large language models: A survey with emphasis on ChatGPT,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 1, pp. 1–26, Jan. 2025. doi: 10.1109/JAS.2024.124983
Citation: W. Zhou, X. Zhu, Q.-L. Han, L. Li, X. Chen, S. Wen, and Y. Xiang, “The security of using large language models: A survey with emphasis on ChatGPT,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 1, pp. 1–26, Jan. 2025. doi: 10.1109/JAS.2024.124983
shu

The Security of Using Large Language Models: A Survey With Emphasis on ChatGPT

doi: 10.1109/JAS.2024.124983
More Information
    Abstract
  • ChatGPT is a powerful artificial intelligence (AI) language model that has demonstrated significant improvements in various natural language processing (NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse, attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future directions. Through this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.

     

    • FullText(HTML)
  • loading
    • References(177)
  • [1]
    Q. Miao, W. Zheng, Y. Lv, M. Huang, W. Ding, and F.-Y. Wang, “DAO to HANOI via DeSci: AI paradigm shifts from AlphaGo to ChatGPT,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 877–897, Apr. 2023. doi: 10.1109/JAS.2023.123561
    [2]
    Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015. doi: 10.1038/nature14539
    [3]
    T. Wu, S. He, J. Liu, S. Sun, K. Liu, Q.-L. Han, and Y. Tang, “A brief overview of ChatGPT: The history, status quo and potential future development,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 5, pp. 1122–1136, May 2023. doi: 10.1109/JAS.2023.123618
    [4]
    OpenAI, “Introducing ChatGPT,” [Online]. Available: https://openai.com/blog/chatgpt, November 30, 2022.
    [5]
    W. D. Heaven, “OpenAI’s new language generator GPT-3 is shockingly good—and completely mindless,” [Online]. Available: https://www.technologyreview.com/2020/07/20/1005454/openai-machine-learning-language-generator-gpt-3-nlp/, July 20, 2020.
    [6]
    S. Biswas, “The function of chat GPT in social media: According to chat GPT,” 2023.
    [7]
    H. Hassani and E. S. Silva, “The role of ChatGPT in data science: How AI-assisted conversational interfaces are revolutionizing the field,” Big Data Cogn. Comput, vol. 7, no. 2, p. 62, Mar. 2023. doi: 10.3390/bdcc7020062
    [8]
    T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, “Language models are few-shot learners,” in Proc. 34th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2020, pp. 159.
    [9]
    F.-Y. Wang, Q. Miao, X. Li, X. Wang, and Y. Lin, “What does ChatGPT say: The DAO from algorithmic intelligence to linguistic intelligence,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 3, pp. 575–579, Mar. 2023. doi: 10.1109/JAS.2023.123486
    [10]
    C. Guo, Y. Lu, Y. Dou, and F.-Y. Wang, “Can ChatGPT boost artistic creation: The need of imaginative intelligence for parallel art,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 835–838, Apr. 2023. doi: 10.1109/JAS.2023.123555
    [11]
    D. Baidoo-Anu and L. Owusu Ansah, “Education in the era of generative artificial intelligence (AI): Understanding the potential benefits of ChatGPT in promoting teaching and learning,” J. AI, vol. 7, no. 1, pp. 52–62, Jan.–Dec. 2023. doi: 10.61969/jai.1337500
    [12]
    B. D. Lund and T. Wang, “Chatting about ChatGPT: How may AI and GPT impact academia and libraries?,” Lib. Hi Tech News, vol. 40, no. 3, pp. 26–29, May 2023. doi: 10.1108/LHTN-01-2023-0009
    [13]
    S. Sok and K. Heng, “ChatGPT for education and research: A review of benefits and risks,” SSRN, Mar 2023.
    [14]
    D. Kalla, N. Smith, S. Kuraku, and F. Samaah., “Study and analysis of chat GPT and its impact on different fields of study,” Int. J. Innovative Sci. Res. Technol., vol. 8, no. 3, pp. 827–833, Mar. 2023.
    [15]
    X. Xue, X. Yu, and F.-Y. Wang, “ChatGPT chats on computational experiments: From interactive intelligence to imaginative intelligence for design of artificial societies and optimization of foundational models,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1357–1360, Jun. 2023. doi: 10.1109/JAS.2023.123585
    [16]
    F.-Y. Wang, J. Yang, X. Wang, J. Li, and Q.-L. Han, “Chat with ChatGPT on industry 5.0: Learning and decision-making for intelligent industries,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 831–834, Apr. 2023. doi: 10.1109/JAS.2023.123552
    [17]
    D. M. Korngiebel and S. D. Mooney, “Considering the possibilities and pitfalls of generative pre-trained transformer 3 (GPT-3) in healthcare delivery,” NPJ Digital Med., vol. 4, no. 1, p. 93, Jun. 2021. doi: 10.1038/s41746-021-00464-x
    [18]
    M. Sallam, “ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns,” Healthcare, vol. 11, no. 6, p. 887, Mar. 2023. doi: 10.3390/healthcare11060887
    [19]
    S. S. Biswas, “Role of chat GPT in public health,” Ann. Biomed. Eng., vol. 51, no. 5, pp. 868–869, Mar. 2023. doi: 10.1007/s10439-023-03172-7
    [20]
    M. Sallam, N. Salim, M. Barakat, and A. Al-Tammemi, “ChatGPT applications in medical, dental, pharmacy, and public health education: A descriptive study highlighting the advantages and limitations,” Narra J., vol. 3, no. 1, p. e103, Mar. 2023. doi: 10.52225/narra.v3i1.103
    [21]
    M. Sallam, “The utility of ChatGPT as an example of large language models in healthcare education, research and practice: Systematic review on the future perspectives and potential limitations,” medRxiv, 2023, DOI: 10.1101/2023.02.19.23286155.
    [22]
    A. Ausekar and R. Bhagwat, “Banking on AI: Exploring the transformative role of ChatGPT in financial services,” in Proc. IEEE Engineering Informatics, Melbourne, Australia, Nov. 2023, pp. 1−6.
    [23]
    P. Rivas and L. Zhao, “Marketing with ChatGPT: Navigating the ethical terrain of GPT-based chatbot technology,” AI, vol. 4, no. 2, pp. 375–384, Apr. 2023. doi: 10.3390/ai4020019
    [24]
    G. F. Frederico, “ChatGPT in supply chains: Initial evidence of applications and potential research agenda,” Logistics, vol. 7, no. 2, p. 26, Apr. 2023. doi: 10.3390/logistics7020026
    [25]
    I. Carvalho and S. Ivanov, “ChatGPT for tourism: Applications, benefits and risks,” Tourism Rev., vol. 79, no. 2, pp. 290–303, Feb. 2024. doi: 10.1108/TR-02-2023-0088
    [26]
    B. Ahmad, S. Thakur, B. Tan, R. Karri, and H. Pearce, “Fixing hardware security bugs with large language models,” arXiv preprint arXiv: 2302.01215, 2023.
    [27]
    C. S. Xia and L. Zhang, “Conversational automated program repair,” arXiv preprint arXiv: 2301.13246, 2023.
    [28]
    D. Sobania, M. Briesch, C. Hanna, and J. Petke, “An analysis of the automatic bug fixing performance of ChatGPT,” in Proc. IEEE/ACM Int. Workshop on Automated Program Repair, Melbourne, Australia, 2023, pp. 1–8.
    [29]
    M. Nair, R. Sadhukhan, and D. Mukhopadhyay, “Generating secure hardware using ChatGPT resistant to CWEs,” Cryptology ePrint Archive, 2023.
    [30]
    N. M. S. Surameery and M. Y. Shakor, “Use chat GPT to solve programming bugs,” Int. J. Inf. Technol. Comput. Eng., vol. 3, no. 1, pp. 17–22, Dec. 2022.
    [31]
    Twingate Team, “What happened in the ChatGPT data breach?” [Online]. Available: https://www.twingate.com/blog/tips/chatgpt-data-breach, August 2, 2023.
    [32]
    A. Mudaliar, “Samsung bans ChatGPT for staff, Microsoft hints potential alternative,” [Online]. Available: https://www.spiceworks.com/tech/artificial-intelligence/news/samsung-bans-chatgpt-for-staff/, August 2, 2023.
    [33]
    B. Guembe, A. Azeta, S. Misra, V. C. Osamor, L. Fernandez-Sanz, and V. Pospelova, “The emerging threat of AI-driven cyber attacks: A review,” Appl. Artif. Intell., vol. 36, no. 1, p. 2037254, Mar. 2022. doi: 10.1080/08839514.2022.2037254
    [34]
    Y. Himeur, S. S. Sohail, F. Bensaali, A. Amira, and M. Alazab, “Latest trends of security and privacy in recommender systems: A comprehensive review and future perspectives,” Comput. Secur., vol. 118, p. 102746, Jul. 2022. doi: 10.1016/j.cose.2022.102746
    [35]
    A. Mascellino, “New research exposes security risks in ChatGPT plugins,” [Online]. Available: https://www.infosecurity-magazine.com/news/security-risks-chatgpt-plugins, August 2, 2023.
    [36]
    S. L. Blodgett, S. Barocas, H. Daumé Ⅲ, and H. Wallach, “Language (technology) is power: A critical survey of ‘bias’ in NLP,” in Proc. 58th Annu. Meeting of the Association for Computational Linguistics, 2020, pp. 5454–5476.
    [37]
    E. Sheng, K.-W. Chang, P. Natarajan, and N. Peng, “Societal biases in language generation: Progress and challenges,” in Proc. 59th Annu. Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. Natural Language Processing, 2021, pp. 4275-4293.
    [38]
    M. Hasal, J. Nowaková, K. Ahmed Saghair, H. Abdulla, V. Snášel, and L. Ogiela, “Chatbots: Security, privacy, data protection, and social aspects,” Concurrency Comput.: Pract. Exper., vol. 33, no. 19, p. e6426, Jun. 2021. doi: 10.1002/cpe.6426
    [39]
    J. Pu, Z. Sarwar, S. M. Abdullah, A. Rehman, Y. Kim, P. Bhattacharya, M. Javed, and B. Viswanath, “Deepfake text detection: Limitations and opportunities,” in Proc. IEEE Symp. Security and Privacy, San Francisco, USA, 2023, pp. 1613–1630.
    [40]
    L. Weidinger, J. Uesato, M. Rauh, C. Griffin, P.-S. Huang, J. Mellor, A. Glaese, M. Cheng, B. Balle, A. Kasirzadeh, C. Biles, S. Brown, Z. Kenton, W. Hawkins, T. Stepleton, A. Birhane, L. A. Hendricks, L. Rimell, W. Isaac, J. Haas, S. Legassick, G. Irving, and I. Gabriel, “Taxonomy of risks posed by language models,” in Proc. ACM Conf. Fairness, Accountability, and Transparency, Seoul, Republic of Korea, 2022, pp. 214–229.
    [41]
    E. Kasneci, K. Sessler, S. Küchemann, M. Bannert, D. Dementieva, F. Fischer, U. Gasser, G. Groh, S. Günnemann, E. Hüllermeier, S. Krusche, G. Kutyniok, T. Michaeli, C. Nerdel, J. Pfeffer, O. Poquet, M. Sailer, A. Schmidt, T. Seidel, M. Stadler, J. Weller, J. Kuhn, and G. Kasneci, “ChatGPT for good? On opportunities and challenges of large language models for education,” Learn. Individual Differ., vol. 103, p. 102274, Apr. 2023. doi: 10.1016/j.lindif.2023.102274
    [42]
    T. Y. Zhuo, Y. Huang, C. Chen, and Z. Xing, “Red teaming ChatGPT via jailbreaking: Bias, robustness, reliability and toxicity,” arXiv preprint arXiv: 2301.12867, 2023.
    [43]
    P. P. Ray, “ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope,” Internet Things Cyber-Phys. Syst., vol. 3, pp. 121–154, Apr. 2023. doi: 10.1016/j.iotcps.2023.04.003
    [44]
    S. Kumar, V. Balachandran, L. Njoo, A. Anastasopoulos, and Y. Tsvetkov, “Language generation models can cause harm: So what can we do about it? An actionable survey,” in Proc. 17th Conf. European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, 2023, pp. 3299–3321.
    [45]
    W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, Y. Du, C. Yang, Y. Chen, Z. Chen, J. Jiang, R. Ren, Y. Li, X. Tang, Z. Liu, P. Liu, J.-Y. Nie, and J.-R. Wen, “A survey of large language models,” arXiv preprint arXiv: 2303.18223, 2023.
    [46]
    J. Deng, H. Sun, Z. Zhang, J. Cheng, and M. Huang, “Recent advances towards safe, responsible, and moral dialogue systems: A survey,” arXiv preprint arXiv: 2302.09270, 2023.
    [47]
    C. Dilmegani, “Large language model training,” [Online]. Available: https://research.aimultiple.com/large-language-model-training/, August 2, 2023.
    [48]
    OpenAI, “Safety at every step,” [Online]. Available: https://openai.com/safety, August 2, 2023.
    [49]
    C. Yeo and A. Chen, “Defining and evaluating fair natural language generation,” in Proc. Fourth Widening Natural Language Processing Workshop, Seattle, USA, 2020, pp. 107–109.
    [50]
    L. Lucy and D. Bamman, “Gender and representation bias in GPT-3 generated stories,” in Proc. Third Workshop on Narrative Understanding, 2021, pp. 48–55.
    [51]
    J. Shihadeh, M. Ackerman, A. Troske, N. Lawson, and E. Gonzalez, “Brilliance bias in GPT-3,” in Proc. IEEE Global Humanitarian Technology Conf., Santa Clara, USA, 2022, pp. 62–69.
    [52]
    D. M. Kaplan, R. Palitsky, S. J. Arconada Alvarez, N. S. Pozzo, M. N. Greenleaf, C. A. Atkinson, and W. A. Lam, “What’s in a name? Experimental evidence of gender bias in recommendation letters generated by ChatGPT,” J. Med. Int. Res., vol. 26, p. e51837, Mar. 2024.
    [53]
    W. Guo and A. Caliskan, “Detecting emergent intersectional biases: Contextualized word embeddings contain a distribution of human-like biases,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, New York, USA, 2021, pp. 122–133.
    [54]
    M. Nadeem, A. Bethke, and S. Reddy, “StereoSet: Measuring stereotypical bias in pretrained language models,” in Proc. 59th Annu. Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. Natural Language Processing, 2021, pp. 5356–5371.
    [55]
    C. Logé, E. Ross, D. Y. A. Dadey, S. Jain, A. Saporta, A. Y. Ng, and P. Rajpurkar, “Q-pain: A question answering dataset to measure social bias in pain management,” in Proc. 35th Conf. Neural Information Processing Systems, 2021, pp. 1–12.
    [56]
    K. S. Amin, H. P. Forman, and M. A. Davis, “Even with ChatGPT, race matters,” Clin. Imaging, vol. 109, pp. 110–113, May 2024.
    [57]
    E. Sheng, K.-W. Chang, P. Natarajan, and N. Peng, “The woman worked as a babysitter: On biases in language generation,” in Proc. Conf. Empirical Methods in Natural Language Processing and the 9th Int. Joint Conf. Natural Language Processing, Hong Kong, China, 2019, pp. 3407–3412.
    [58]
    A. Zheng, “Dissecting bias of ChatGPT in college major recommendations,” Inf. Technol. Manage., 2024, DOI: 10.1007/s10799-024-00430-5.
    [59]
    L. Lippens, “Computer says ‘no’: Exploring systemic bias in ChatGPT using an audit approach,” Comput. Hum. Behav.: Artif. Humans, vol. 2, no. 1, p. 100054, Jan.–Jul. 2024. doi: 10.1016/j.chbah.2024.100054
    [60]
    A. Abid, M. Farooqi, and J. Zou, “Persistent anti-muslim bias in large language models,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, New York, USA, 2021, pp. 298–306.
    [61]
    A. Abid, M. Farooqi, and J. Zou, “Large language models associate muslims with violence,” Nat. Mach. Intell., vol. 3, no. 6, pp. 461–463, Jun. 2021. doi: 10.1038/s42256-021-00359-2
    [62]
    A. Al Amin and K. S. Kabir, “A disability lens towards biases in GPT-3 generated open-ended languages,” arXiv preprint arXiv: 2206.11993, 2022.
    [63]
    L. Gover, “Political bias in large language models,” The Commons: Puget Sound Journal of Politics, vol. 4, no. 1, pp. 11–22, 2023.
    [64]
    P. Pit, X. Ma, M. Conway, Q. Chen, J. Bailey, H. Pit, P. Keo, W. Diep, and Y.-G. Jiang, “Whose side are you on? Investigating the political stance of large language models,” arXiv preprint arXiv: 2403.13840, 2024.
    [65]
    Y. Bang, D. Chen, N. Lee, and P. Fung, “Measuring political bias in large language models: What is said and how it is said,” in Proc. 62nd Annu. Meeting of the Association for Computational Linguistics, Bangkok, Thailand, 2024, pp. 11142–11159.
    [66]
    J. Hartmann, J. Schwenzow, and M. Witte, “The political ideology of conversational AI: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation,” arXiv preprint arXiv: 2301.01768, 2023.
    [67]
    D. Rozado, “The political biases of ChatGPT,” Soc. Sci., vol. 12, no. 3, p. 148, Mar. 2023. doi: 10.3390/socsci12030148
    [68]
    R. W. McGee, “Is chat GPT biased against conservatives? An empirical study,” SSRN Electron. J., 2023, DOI: 10.2139/ssrn.4359405.
    [69]
    F. Motoki, V. Pinho Neto, and V. Rodrigues, “More human than human: Measuring ChatGPT political bias,” Public Choice, vol. 198, no. 1–2, pp. 3–23, Jan. 2024. doi: 10.1007/s11127-023-01097-2
    [70]
    N. Retzlaff, “Political biases of ChatGPT in different languages,” 2024.
    [71]
    J. Rutinowski, S. Franke, J. Endendyk, I. Dormuth, M. Roidl, and M. Pauly, “The self-perception and political biases of ChatGPT,” Hum. Behav. Emerging Technol., vol. 2024, no. 1, p. 7115633, Jan. 2024.
    [72]
    S. Gehman, S. Gururangan, M. Sap, Y. Choi, and N. A. Smith, “RealToxicityPrompts: Evaluating neural toxic degeneration in language models,” in Proc. Association for Computational Linguistics: EMNLP 2020, 2020, pp. 3356–3369.
    [73]
    N. Ousidhoum, X. Zhao, T. Fang, Y. Song, and D.-Y. Yeung, “Probing toxic content in large pre-trained language models,” in Proc. 59th Annu. Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. Natural Language Processing, 2021, pp. 4262–4274.
    [74]
    D. Nozza, F. Bianchi, and D. Hovy, “HONEST: Measuring hurtful sentence completion in language models,” in Proc. Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 2398–2406.
    [75]
    P. Schramowski, C. Turan, N. Andersen, C. A. Rothkopf, and K. Kersting, “Large pre-trained language models contain human-like biases of what is right and wrong to do,” Nat. Mach. Intell., vol. 4, no. 3, pp. 258–268, Mar. 2022. doi: 10.1038/s42256-022-00458-8
    [76]
    T. Hartvigsen, S. Gabriel, H. Palangi, M. Sap, D. Ray, and E. Kamar, “ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection,” in Proc. 60th Annu. Meeting of the Association for Computational Linguistics, Dublin, Ireland, 2022, pp. 3309–3326.
    [77]
    F. Huang, H. Kwak, and J. An, “Is ChatGPT better than human annotators? Potential and limitations of ChatGPT in explaining implicit hate speech,” in Proc. ACM Web Conf., Austin, USA, 2023, pp. 294–297.
    [78]
    P.-S. Huang, H. Zhang, R. Jiang, R. Stanforth, J. Welbl, J. Rae, V. Maini, D. Yogatama, and P. Kohli, “Reducing sentiment bias in language models via counterfactual evaluation,” in Proc. Association for Computational Linguistics: EMNLP 2020, 2020, pp. 65–83.
    [79]
    E. Sheng, K.-W. Chang, P. Natarajan, and N. Peng, “Towards controllable biases in language generation,” in Proc. Association for Computational Linguistics: EMNLP 2020, 2020, pp. 3239–3254.
    [80]
    P. P. Liang, C. Wu, L.-P. Morency, and R. Salakhutdinov, “Towards understanding and mitigating social biases in language models,” in Proc. 38th Int. Conf. Machine Learning, 2021, pp. 6565–6576.
    [81]
    C. Borchers, D. Gala, B. Gilburt, E. Oravkin, W. Bounsi, Y. M. Asano, and H. Kirk, “Looking for a handsome carpenter! Debiasing GPT-3 job advertisements,” in Proc. 4th Workshop on Gender Bias in Natural Language Processing, Seattle, USA, 2022, pp. 212–224.
    [82]
    R. Liu, C. Jia, J. Wei, G. Xu, L. Wang, and S. Vosoughi, “Mitigating political bias in language models through reinforced calibration,” in Proc. 35th AAAI Conf. Artificial Intelligence, 2021, pp. 14857–14866.
    [83]
    R. Liu, C. Jia, J. Wei, G. Xu, and S. Vosoughi, “Quantifying and alleviating political bias in language models,” Artif. Intell., vol. 304, p. 103654, Mar. 2022. doi: 10.1016/j.artint.2021.103654
    [84]
    J. Welbl, A. Glaese, J. Uesato, S. Dathathri, J. Mellor, L. A. Hendricks, K. Anderson, P. Kohli, B. Coppin, and P.-S. Huang, “Challenges in detoxifying language models,” in Proc. Association for Computational Linguistics, Punta Cana, Dominican Republic, 2021, pp. 2447–2469.
    [85]
    A. Xu, E. Pathak, E. Wallace, S. Gururangan, M. Sap, and D. Klein, “Detoxifying language models risks marginalizing minority voices,” in Proc. Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 2390–2397.
    [86]
    N. Inie, J. Falk Olesen, and L. Derczynski, “The Rumour mill: Making the spread of misinformation explicit and tangible,” in Proc. CHI Conf. Human Factors in Computing Systems, Honolulu, USA, 2020, pp. 1–4.
    [87]
    S. Kreps, R. M. McCain, and M. Brundage, “All the news that’s fit to fabricate: AI-generated text as a tool of media misinformation,” J. Exp. Polit. Sci., vol. 9, no. 1, pp. 104–117, Nov. 2022. doi: 10.1017/XPS.2020.37
    [88]
    G. Spitale, N. Biller-Andorno, and F. Germani, “AI model GPT-3 (dis)informs us better than humans,” Sci. Adv., vol. 9, no. 26, p. eadh1850, Jun. 2023. doi: 10.1126/sciadv.adh1850
    [89]
    H. Y. Li, “The possibility and optimization path of ChatGPT promoting the generation and dissemination of fake news,” Media Commun. Res., vol. 5, no. 2, pp. 80–86, 2024.
    [90]
    P. Ranade, A. Piplai, S. Mittal, A. Joshi, and T. Finin, “Generating fake cyber threat intelligence using transformer-based models,” in Proc. Int. Joint Conf. Neural Networks, Shenzhen, China, 2021, pp. 1–9.
    [91]
    J. Mink, L. Luo, N. M. Barbosa, O. Figueira, Y. Wang, and G. Wang, “DeepPhish: Understanding user trust towards artificially generated profiles in online social networks,” in Proc. 31st USENIX Security Symp., Boston, USA, 2022, pp. 1669–1686.
    [92]
    Y. Hu, Y. Lin, E. Skorupa Parolin, L. Khan, and K. Hamlen, “Controllable fake document infilling for cyber deception,” in Proc. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 2022, pp. 6505–6519.
    [93]
    D. Barman, Z. Guo, and O. Conlan, “The dark side of language models: Exploring the potential of LLMs in multimedia disinformation generation and dissemination,” Mach. Learn. Appl., vol. 16, p. 100545, Jun. 2024.
    [94]
    R. Zellers, A. Holtzman, H. Rashkin, Y. Bisk, A. Farhadi, F. Roesner, and Y. Choi, “Defending against neural fake news,” in Proc. 33rd Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2019, pp. 812.
    [95]
    H. Stiff and F. Johansson, “Detecting computer-generated disinformation,” Int. J. Data Sci. Anal., vol. 13, no. 4, pp. 363–383, May 2022. doi: 10.1007/s41060-021-00299-5
    [96]
    S. Rossi, Y. Kwon, O. H. Auglend, R. R. Mukkamala, M. Rossi, and J. Thatcher, “Are deep learning-generated social media profiles indistinguishable from real profiles?” in Proc. 56th Hawaii Int. Conf. System Sciences, 2023, pp. 134–143.
    [97]
    A. Gupta, A. Singhal, A. Mahajan, A. Jolly, and S. Kumar, “Empirical framework for automatic detection of neural and human authored fake news,” in Proc. 6th Int. Conf. Intelligent Computing and Control Systems, Madurai, India, 2022, pp. 1625–1633.
    [98]
    A. Pagnoni, M. Graciarena, and Y. Tsvetkov, “Threat scenarios and best practices to detect neural fake news,” in Proc. 29th Int. Conf. Computational Linguistics, Gyeongju, South Korea, 2022, pp. 1233–1249.
    [99]
    M. Gambini, T. Fagni, F. Falchi, and M. Tesconi, “On pushing DeepFake tweet detection capabilities to the limits,” in Proc. 14th ACM Web Science Conf., Barcelona, Spain, 2022, pp. 154–163.
    [100]
    B. Jiang, Z. Tan, A. Nirmal, and H. Liu, “Disinformation detection: An evolving challenge in the age of LLMs,” in Proc. SIAM Int. Conf. Data Mining, 2024, pp. 427–435.
    [101]
    Y. Huang, K. Shu, P. S. Yu, and L. Sun, “From creation to clarification: ChatGPT’s journey through the fake news quagmire,” in Companion Proc. ACM Web Conf., Singapore, Singapore, 2024, pp. 513–516.
    [102]
    S. B. Shah, S. Thapa, A. Acharya, K. Rauniyar, S. Poudel, S. Jain, A. Masood, and U. Naseem, “Navigating the web of disinformation and misinformation: Large language models as double-edged swords,” IEEE Access, 2024, DOI: 10.1109/ACCESS.2024.3406644.
    [103]
    Y. Tukmacheva, I. Oseledets, and E. Frolov, “Mitigating human and computer opinion fraud via contrastive learning,” arXiv preprint arXiv: 2301.03025, 2023.
    [104]
    A. Gambetti and Q. Han, “Combat AI with AI: Counteract machine-generated fake restaurant reviews on social media,” arXiv preprint arXiv: 2302.07731, 2023.
    [105]
    P. Henderson, K. Sinha, N. Angelard-Gontier, N. R. Ke, G. Fried, R. Lowe, and J. Pineau, “Ethical challenges in data-driven dialogue systems,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, New Orleans, USA, 2018, pp. 123–129.
    [106]
    K. McGuffie and A. Newhouse, “The radicalization risks of GPT-3 and advanced neural language models,” arXiv preprint arXiv: 2009.06807, 2020.
    [107]
    T. Y. Zhuo, Y. Huang, C. Chen, and Z. Xing, “Exploring AI ethics of ChatGPT: A diagnostic analysis,” arXiv preprint arXiv: 2301.12867, 2023.
    [108]
    A. Borji, “A categorical archive of ChatGPT failures,” arXiv preprint arXiv: 2302.03494, 2023.
    [109]
    A. Rasekh and I. Eisenberg, “Democratizing ethical assessment of natural language generation models,” arXiv preprint arXiv: 2207.10576, 2022.
    [110]
    A. Chan, “GPT-3 and instructGPT: Technological dystopianism, utopianism, and “contextual” perspectives in AI ethics and industry,” AI Ethics, vol. 3, no. 1, pp. 53–64, Feb. 2023. doi: 10.1007/s43681-022-00148-6
    [111]
    J. Chatterjee and N. Dethlefs, “This new conversational AI model can be your friend, philosopher, and guide.. and even your worst enemy,” Patterns, vol. 4, no. 1, p. 100676, Jan. 2023. doi: 10.1016/j.patter.2022.100676
    [112]
    R. Karanjai, “Targeted phishing campaigns using large scale language models,” arXiv preprint arXiv: 2301.00665, 2023.
    [113]
    H. Khan, M. Alam, S. Al-Kuwari, and Y. Faheem, “Offensive AI: Unification of email generation through GPT-2 model with a game-theoretic approach for spear-phishing attacks,” in Proc. Competitive Advantage in the Digital Economy, 2021, pp. 178–184.
    [114]
    A. M. Shibli, M. M. A. Pritom, and M. Gupta, “AbuseGPT: Abuse of generative AI ChatBots to create smishing campaigns,” in Proc. 12th Int. Symp. Digital Forensics and Security, San Antonio, USA, 2024, pp. 1–6.
    [115]
    P. V. Falade, “Deciphering ChatGPT’s impact: Exploring its role in cybercrime and cybersecurity,” Int. J. Sci. Res. Comput. Sci. Eng., vol. 12, no. 2, pp. 15–24, Apr. 2024.
    [116]
    M. Alawida, B. Abu Shawar, O. I. Abiodun, A. Mehmood, A. E. Omolara, and A. K. Al Hwaitat, “Unveiling the dark side of ChatGPT: Exploring cyberattacks and enhancing user awareness,” Information, vol. 15, no. 1, p. 27, Jan. 2024. doi: 10.3390/info15010027
    [117]
    L. Alotaibi, S. Seher, and N. Mohammad, “Cyberattacks using ChatGPT: Exploring malicious content generation through prompt engineering,” in Proc. ASU Int. Conf. Emerging Technologies for Sustainability and Intelligent Systems, Manama, Bahrain, 2024, pp. 1304–1311.
    [118]
    T. Susnjak, “ChatGPT: The end of online exam integrity?” arXiv preprint arXiv: 2212.09292, 2022.
    [119]
    C. A. Gao, F. M. Howard, N. S. Markov, E. C. Dyer, S. Ramesh, Y. Luo, and A. T. Pearson, “Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers,” npj Digit. Med., vol. 6, no. 1, p. 75, Apr. 2023. doi: 10.1038/s41746-023-00819-6
    [120]
    M. J. Israel and A. Amer, “Rethinking data infrastructure and its ethical implications in the face of automated digital content generation,” AI Ethics, vol. 3, no. 2, pp. 427–439, May 2023. doi: 10.1007/s43681-022-00169-1
    [121]
    S. Jalil, S. Raff, T. D. LaToza, K. Moran, and W. Lam, “ChatGPT and software testing education: Promises & perils,” in Proc. IEEE Int. Conf. Software Testing, Verification and Validation Workshops, Dublin, Ireland, 2023, pp. 4130–4137.
    [122]
    A. B. Armstrong, “Who’s afraid of ChatGPT? An examination of ChatGPT’s implications for legal writing,” Tech. Rep., 2023.
    [123]
    D. R. E Cotton, P. A. Cotton, and J. R. Shipway, “Chatting and cheating: Ensuring academic integrity in the era of ChatGPT,” Innovations Educ. Teach. Int, vol. 61, no. 2, pp. 228–239, Mar. 2023.
    [124]
    R. J. M. Ventayen, “OpenAI ChatGPT-generated results: Similarity index of artificial intelligence-based contents,” in Soft Computing for Security Applications, G. Ranganathan, Y. El Allioui, and S. Piramuthu, Eds. Singapore, Singapore: Springer, 2023, pp. 215–226.
    [125]
    M. Khalil and E. Er, “Will ChatGPT get you caught? Rethinking of plagiarism detection,” Proc. 10th Int. Conf. Learning and Collaboration Technologies, Copenhagen, Denmark, 2023, pp. 475–487.
    [126]
    M. Rezaei, H. Salehi, and O. Tabatabaei, “Uses and misuses of ChatGPT as an AI-language model in academic writing,” in Proc. 10th Int. Conf. Artificial Intelligence and Robotics, Qazvin, Islamic Republic of, 2024, pp. 256–260.
    [127]
    R. Mustapha, S. N. A. M. Mustapha, and F. W. A. Mustapha, “Students’ misuse of ChatGPT in higher education: An application of the fraud triangle theory,” J. Contemp. Soc. Sci. Educ. Stud., vol. 4, no. 1, pp. 87–97, Apr. 2024.
    [128]
    M. M. Van Wyk, “Is ChatGPT an opportunity or a threat? Preventive strategies employed by academics related to a GenAI-based LLM at a faculty of education,” J. Appl. Learn. Teach., vol. 7, no. 1, pp. 1–35, Feb. 2024.
    [129]
    M. P. Rogers, H. M. Hillberg, and C. L. Groves, “Attitudes towards the use (and misuse) of ChatGPT: A preliminary study,” in Proc. 55th ACM Tech. Symp. Computer Science Education, Portland, USA, 2024, pp. 1147–1153.
    [130]
    N. M. Mbwambo and P. B. Kaaya, “ChatGPT in education: Applications, concerns and recommendations,” J. ICT Syst., vol. 2, no. 1, pp. 107–124, Jun. 2024. doi: 10.56279/jicts.v2i1.87
    [131]
    G. Kendall and J. A. T. da Silva, “Risks of abuse of large language models, like ChatGPT, in scientific publishing: Authorship, predatory publishing, and paper mills,” Learn. Publ., vol. 37, no. 1, pp. 55–62, Jan. 2024. doi: 10.1002/leap.1578
    [132]
    M. Dowling and B. Lucey, “ChatGPT for (finance) research: The Bananarama conjecture,” Finance Res. Lett., vol. 53, p. 103662, May 2023. doi: 10.1016/j.frl.2023.103662
    [133]
    H. H. Thorp, “ChatGPT is fun, but not an author,” Science, vol. 379, no. 6630, pp. 313–313, Jan. 2023. doi: 10.1126/science.adg7879
    [134]
    M. Liebrenz, R. Schleifer, A. Buadze, D. Bhugra, and A. Smith, “Generating scholarly content with ChatGPT: Ethical challenges for medical publishing,” Lancet Digital Health, vol. 5, no. 3, pp. e105–e106, Mar. 2023. doi: 10.1016/S2589-7500(23)00019-5
    [135]
    F. M. Megahed, Y.-J. Chen, J. A. Ferris, S. Knoth, and L. A. Jones-Farmer, “How generative AI models such as ChatGPT can be (mis)used in SPC practice, education, and research? An exploratory study,” Qual. Eng., pp. 287–315, Jun. 2023.
    [136]
    J. Albrecht, E. Kitanidis, and A. Fetterman, “Despite “super-human” performance, current LLMs are unsuited for decisions about ethics and safety,” in Proc. 36th Conf. Neural Information Processing Systems, New Orleans, USA, 2022.
    [137]
    S. Krügel, A. Ostermaier, and M. Uhl, “The moral authority of ChatGPT,” arXiv preprint arXiv: 2301.07098, 2023.
    [138]
    M. Jakesch, A. Bhat, D. Buschek, L. Zalmanson, and M. Naaman, “Co-writing with opinionated language models affects users’ views,” in Proc. 2023 CHI Conf. Human Factors in Computing Systems, Hamburg, Germany, 2023, pp. 111.
    [139]
    The Lancet Digital Health, “ChatGPT: Friend or foe?” Lancet Digital Health, vol. 5, no. 3, pp. E102, Mar. 2023.
    [140]
    H. Zohny, J. McMillan, and M. King, “Ethics of generative AI,” J. Med. Ethics, vol. 49, no. 2, pp. 79–80, Feb. 2023. doi: 10.1136/jme-2023-108909
    [141]
    W. Chen, F. Wang, and M. Edwards, “Active countermeasures for email fraud,” in Proc. 8th IEEE European Symp. Security and Privacy, Delft, Netherlands, 2023, pp. 39–55.
    [142]
    J. Hewett and M. Leeke, “Developing a GPT-3-based automated victim for advance fee fraud disruption,” in Proc. IEEE 27th Pacific Rim Int. Symp. Dependable Computing, Beijing, China, 2022, pp. 205–211.
    [143]
    P. Hacker, A. Engel, and M. Mauer, “Regulating ChatGPT and other large generative AI models,” in Proc. ACM Conf. Fairness, Accountability, and Transparency, Chicago, USA, 2023, pp. 1112–1123.
    [144]
    M. Y. Vardi, “Who is responsible around here?,” Commun. ACM, vol. 66, no. 3, p. 5, Feb. 2023. doi: 10.1145/3580584
    [145]
    O. Oviedo-Trespalacios, A. E. Peden, T. Cole-Hunter, A. Costantini, M. Haghani, J. Rod, S. Kelly, H. Torkamaan, A. Tariq, J. D. A. Newton, T. Gallagher, S. Steinert, A. J. Filtness, G. Reniers, “The risks of using ChatGPT to obtain common safety-related information and advice,” Saf. Sci., vol. 167, p. 106244, Nov. 2023. doi: 10.1016/j.ssci.2023.106244
    [146]
    E. Wallace, S. Feng, N. Kandpal, M. Gardner, and S. Singh, “Universal adversarial triggers for attacking and analyzing NLP,” in Proc. Conf. Empirical Methods in Natural Language Processing and the 9th Int. Joint Conf. Natural Language Processing, Hong Kong, China,, 2019, pp. 2153–2162.
    [147]
    H. S. Heidenreich and J. R. Williams, “The earth is flat and the sun is not a star: The susceptibility of GPT-2 to universal adversarial triggers,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, New York, USA, 2021, pp. 566–573.
    [148]
    F. Perez and I. Ribeiro, “Ignore previous prompt: Attack techniques for language models,” in Proc. 36th Conf. Neural Information Processing Systems, New Orleans, USA, 2022, pp. 1–21.
    [149]
    K. Greshake, S. Abdelnabi, S. Mishra, C. Endres, T. Holz, and M. Fritz, “More than you’ve asked for: A comprehensive analysis of novel prompt injection threats to application-integrated large language models,” arXiv preprint arXiv: 2302.12173, 2023.
    [150]
    Y. Liu, G. Deng, Z. Xu, Y. Li, Y. Zheng, Y. Zhang, L. Zhao, T. Zhang, and K. Wang, “A hitchhiker’s guide to jailbreaking ChatGPT via prompt engineering,” in Proc. 4th Int. Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things, Porto de Galinhas Brazil, 2024, pp. 12–21.
    [151]
    Z. Sha and Y. Zhang, “Prompt stealing attacks against large language models,” arXiv preprint arXiv: 2402.12959, 2024.
    [152]
    N. Carlini, F. Tramèr, E. Wallace, M. Jagielski, A. Herbert-Voss, K. Lee, A. Roberts, T. Brown, D. Song, Ú. Erlingsson, A. Oprea, and C. Raffel, “Extracting training data from large language models,” in Proc. 30th USENIX Security Symp, 2021, pp. 2633–2650.
    [153]
    H.-M. Chu, J. Geiping, L. H. Fowl, M. Goldblum, and T. Goldstein, “Panning for gold in federated learning: Targeted text extraction under arbitrarily large-scale aggregation,” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2023.
    [154]
    J. Chu, Z. Sha, M. Backes, and Y. Zhang, “Reconstruct your previous conversations! Comprehensively investigating privacy leakage risks in conversations with GPT models,” arXiv preprint arXiv: 2402.02987, 2024.
    [155]
    C. Wei, K. Chen, Y. Zhao, Y. Gong, L. Xiang, and S. Zhu, “Context injection attacks on large language models,” arXiv preprint arXiv: 2405.20234, 2024.
    [156]
    X. Zhang, Z. Zhang, S. Ji, and T. Wang, “Trojaning language models for fun and profit,” in Proc. IEEE European Symp. Security and Privacy, Vienna, Austria, 2021, pp. 179–197.
    [157]
    S. Li, H. Liu, T. Dong, B. Z. H. Zhao, M. Xue, H. Zhu, and J. Lu, “Hidden backdoors in human-centric language models,” in Proc. ACM SIGSAC Conf. Computer and Communications Security, South Korea, 2021, pp. 3123–3140.
    [158]
    X. Pan, M. Zhang, B. Sheng, J. Zhu, and M. Yang, “Hidden trigger backdoor attack on NLP models via linguistic style manipulation,” in Proc. 31st USENIX Security Symp., Boston, USA, 2022, pp. 3611–3628.
    [159]
    Y. Huang, T. Y. Zhuo, Q. Xu, H. Hu, X. Yuan, and C. Chen, “Training-free lexical backdoor attacks on language models,” in Proc. ACM Web Conf., Austin, USA, 2023, pp. 2198–2208.
    [160]
    H. J. Branch, J. R. Cefalu, J. McHugh, L. Hujer, A. Bahl, D. d. C. Iglesias, R. Heichman, and R. Darwishi, “Evaluating the susceptibility of pre-trained language models via handcrafted adversarial examples,” arXiv preprint arXiv: 2209.02128, 2022.
    [161]
    Y. Liu, G. Shen, G. Tao, S. An, S. Ma, and X. Zhang, “Piccolo: Exposing complex backdoors in NLP transformer models,” in Proc. IEEE Symp. Security and Privacy, San Francisco, USA, 2022, pp. 2025–2042.
    [162]
    D. Kang, X. Li, I. Stoica, C. Guestrin, M. Zaharia, and T. Hashimoto, “Exploiting programmatic behavior of LLMs: Dual-use through standard security attacks,” Proc. 40th Int. Conf. Machine Learning, Honolulu, USA, 2023.
    [163]
    X. Pan, M. Zhang, S. Ji, and M. Yang, “Privacy risks of general-purpose language models,” in Proc. IEEE Symp. Security and Privacy, San Francisco, USA, 2020, pp. 1314–1331.
    [164]
    Q. Xu, L. Qu, Z. Gao, and G. Haffari, “Personal information leakage detection in conversations,” in Proc. Conf. Empirical Methods in Natural Language Processing, 2020, pp. 6567–6580.
    [165]
    J. Huang, H. Shao, and K. C.-C. Chang, “Are large pre-trained language models leaking your personal information?” in Proc. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 2022, pp. 2038–2047.
    [166]
    B. Jayaraman, E. Ghosh, M. Chase, S. Roy, W. Dai, and D. Evans, “Combing for credentials: Active pattern extraction from smart reply,” Proc. IEEE Symp. Security and Privacy, San Francisco, USA, 2024, pp. 1443–1461.
    [167]
    N. Lukas, A. Salem, R. Sim, S. Tople, L. Wutschitz, and S. ZanellaBéguelin, “Analyzing leakage of personally identifiable information in language models,” in Proc. IEEE Symp. Security and Privacy, San Francisco, USA, 2023, pp. 346–363.
    [168]
    F. Mireshghallah, A. Uniyal, T. Wang, D. Evans, and T. Berg-Kirkpatrick, “An empirical analysis of memorization in fine-tuned autoregressive language models,” in Proc. Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 1816–1826.
    [169]
    N. Carlini, D. Ippolito, M. Jagielski, K. Lee, F. Tramer, and C. Zhang, “Quantifying memorization across neural language models,” in Proc. Eleventh Int. Conf. Learning Representations, Kigali, Rwanda, 2023.
    [170]
    D. Ippolito, F. Tramèr, M. Nasr, C. Zhang, M. Jagielski, K. Lee, C. A. Choquette-Choo, and N. Carlini, “Preventing verbatim memorization in language models gives a false sense of privacy,” arXiv preprint arXiv: 2210.17546, 2022.
    [171]
    H. Brown, K. Lee, F. Mireshghallah, R. Shokri, and F. Tramèr, “What does it mean for a language model to preserve privacy?” in Proc. ACM Conf. Fairness, Accountability, and Transparency, Seoul, South Korea, 2022, pp. 2280–2292.
    [172]
    J. Mattern, Z. Jin, B. Weggenmann, B. Schoelkopf, and M. Sachan, “Differentially private language models for secure data sharing,” in Proc. Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 4860–4873.
    [173]
    W. Shi, R. Shea, S. Chen, C. Zhang, R. Jia, and Z. Yu, “Just fine-tune twice: Selective differential privacy for large language models,” in Proc. Conf. Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 6327–6340.
    [174]
    X. Feng, X. Zhu, Q.-L. Han, W. Zhou, S. Wen, and Y. Xiang, “Detecting vulnerability on IoT device firmware: A survey,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 25–41, Jan. 2023. doi: 10.1109/JAS.2022.105860
    [175]
    X. Zhu, S. Wen, S. Camtepe, and Y. Xiang, “Fuzzing: A survey for roadmap,” ACM Comput. Surv., vol. 54, no. 11s, p. 230, Sept. 2022.
    [176]
    X. Zhu and M. Böhme, “Regression greybox fuzzing,” in Proc. ACM SIGSAC Conf. Computer and Communications Security, Republic of Korea, 2021, pp. 2169–2182.
    [177]
    D. Su, P. S. Stanimirović, L. B. Han, and L. Jin, “Neural dynamics for improving optimiser in deep learning with noise considered,” CAAI Trans. Intell. Technol., vol. 9, no. 3, pp. 722–737, Jun. 2024. doi: 10.1049/cit2.12263
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(1)  / Tables(5)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (190) PDF downloads(52) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return