Unveiling security, privacy, and ethical concerns of ChatGPT

Xiaodong Wu; Ran Duan; Jianbing Ni

doi:10.1016/j.jiixd.2023.10.007

您当前的位置：

首页 >

文章列表页 >

Unveiling security, privacy, and ethical concerns of ChatGPT

更新时间：2024-04-17

- Unveiling security, privacy, and ethical concerns of ChatGPT
- Unveiling security, privacy, and ethical concerns of ChatGPT
- 信息与智能学报（英文） 2024年2卷第2期
- 作者机构：
  
  Department of Electrical & Computer Engineering, Queen's University,Kingston,Canada,K7L 3N6
- 作者简介：
- 基金信息：
- DOI：10.1016/j.jiixd.2023.10.007
  中图分类号：
- 纸质出版日期：2024，
扫描看全文
Unveiling security, privacy, and ethical concerns of ChatGPT[J]. 信息与智能学报（英文）, 2024,2(2):102-115.

Xiaodong Wu, Ran Duan, Jianbing Ni. Unveiling security, privacy, and ethical concerns of ChatGPT[J]. Journal of Information and Intelligence, 2024,2(2):102-115.
Unveiling security, privacy, and ethical concerns of ChatGPT[J]. 信息与智能学报（英文）, 2024,2(2):102-115. DOI： 10.1016/j.jiixd.2023.10.007.

Xiaodong Wu, Ran Duan, Jianbing Ni. Unveiling security, privacy, and ethical concerns of ChatGPT[J]. Journal of Information and Intelligence, 2024,2(2):102-115. DOI： 10.1016/j.jiixd.2023.10.007.

摘要

Abstract

This paper delves into the realm of ChatGPT

an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries

such as customer service

education

mental health treatment

personal productivity

and content creation

it is essential to address its security

privacy

and ethical implications. By exploring the upgrade path from GPT-1 to GPT-4

discussing the model's features

limitations

and potential applications

this study aims to shed light on the potential risks of integrating ChatGPT into our daily lives. Focusing on security

privacy

and ethics issues

we highlight the challenges these concerns pose for widespread adoption. Finally

we analyze the open problems in these areas

calling for concerted efforts to ensure the development of secure and ethically sound large language models.

关键词

Keywords

ChatGPTLarge language model (LLM)SecurityPrivacyEthics

references

A. Radford, K. Narasimhan, T. Salimans, I. SutskeverImproving language understanding by generative pre-training (2018) https://api.semanticscholar.org/CorpusID:49313245

J. Devlin, M.W. Chang, K. Lee, K. ToutanovaBERT: Pre-training of deep bidirectional transformers for language understanding (2018) https://arxiv.org/pdf/1810.04805.pdf

S. Ranathunga, E.S.A. Lee, M. Prifti Skenduli, R. Shekhar, M. Alam, R. KaurNeural machine translation for low-resource languages: A survey ACM Computing Surveys, 55 (11) (2023), pp. 1-37

D. Bahdanau, K. Cho, Y. BengioNeural machine translation by jointly learning to align and translate (2014) https://arxiv.org/pdf/1409.0473.pdf

A.N. Çayır, T.S. NavruzEffect of dataset size on deep learning in voice recognition Proceedings of the 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), IEEE (2021), pp. 1-5

A.T. Ali, H.S. Abdullah, M.N. FadhilVoice recognition system using machine learning techniques Materials Today: Proceedings (2021), pp. 1-7

W.S. El-Kassas, C.R. Salama, A.A. Rafea, H.K. MohamedAutomatic text summarization: A comprehensive survey Expert Systems with Applications, 165 (2021), Article 113679

Y. Liu, M. LapataText summarization with pretrained encoders (2019) https://arxiv.org/pdf/1908.08345v2.pdf

A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. SutskeverLanguage models are unsupervised multitask learners OpenAI Blog, 1 (8) (2019), p. 9

T. Brown, B. Mann, N. Ryder, M. Subbiah, J.D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al.Language models are few-shot learners Advances in Neural Information Processing Systems, 33 (2020), pp. 1877-1901

A. Roberts, C. Raffel, N. ShazeerHow much knowledge can you pack into the parameters of a language model? (2020) https://arxiv.org/pdf/2002.08910.pdf

M. Chen, J. Tworek, H. Jun, Q. Yuan, H.P.d.O. Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman, et al.Evaluating large language models trained on code (2021) https://arxiv.org/pdf/2107.03374.pdf

L. Ouyang, J. Wu, X. Jiang, D. Almeida, C.L. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al.Training language models to follow instructions with human feedback (2022) https://arxiv.org/pdf/2203.02155.pdf

Y. Fu, H. Peng, T. KhotHow does GPT obtain its ability? Tracing emergent abilities of language models to their sources Yao Fu’s Notion (2022) https://rb.gy/5ez0w

OpenAIGPT-4 technical report (2023) https://arxiv.org/pdf/2303.08774.pdf

S.S. BiswasPotential use of Chat GPT in global warming Annals of Biomedical Engineering, 51 (6) (2021), pp. 1126-1127

S.S. BiswasRole of Chat GPT in public health Annals of Biomedical Engineering, 51 (5) (2023), pp. 868-869

J.A. Goldstein, G. Sastry, M. Musser, R. DiResta, M. Gentzel, K. SedovaGenerative language models and automated influence operations: Emerging threats and potential mitigations (2023) https://arxiv.org/pdf/2301.04246.pdf

V. Taecharungroj“What can ChatGPT do?” analyzing early reactions to the innovative AI chatbot on Twitter Big Data and Cognitive Computing, 7 (1) (2023), p. 35

S. Kreps, D.L. KrinerThe potential impact of emerging technologies on democratic representation: Evidence from a field experiment New Media and Society (2023)

H. Bai, J. Voelkel, J. Eichstaedt, R. WillerArtificial intelligence can persuade humans on political issues (2023), 10.21203/rs.3.rs-3238396/v1

A. Lu, H. Zhang, Y. Zhang, X. Wang, D. YangBounding the capabilities of large language models in open text generation with prompt constraints (2023) https://arxiv.org/pdf/2302.09185.pdf

N. Kaloudi, J. LiThe AI-based cyber threat landscape: A survey ACM Computing Surveys (CSUR), 53 (1) (2020), pp. 1-34

W.R. Huang, J. Geiping, L. Fowl, G. Taylor, T. GoldsteinMetapoison: Practical general-purpose clean-label data poisoning Advances in Neural Information Processing Systems, 33 (2020), pp. 12080-12091

P. Kairouz, H.B. McMahan, B. Avent, A. Bellet, M. Bennis, A.N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, et al.Advances and open problems in federated learning Foundations and Trends® in Machine Learning, 14 (1-2) (2021), pp. 1-210

W. Issa, N. Moustafa, B. Turnbull, N. Sohrabi, Z. TariBlockchain-based federated learning for securing Internet of Things: A comprehensive survey ACM Computing Surveys, 55 (9) (2023), pp. 1-43

G. Wu, M. Hashemi, C. SrinivasaPUMA: Performance unchanged model augmentation for training data removal Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, Menlo Park (2022), pp. 8675-8682

Y. Cao, A.F. Yu, A. Aday, E. Stahl, J. Merwine, J. YangEfficient repair of polluted machine learning systems via causal unlearning Proceedings of the 2018 on Asia Conference on Computer and Communications Security, Association for Computing Machinery, New York (2018), pp. 735-747

B. Biggio, B. Nelson, P. LaskovPoisoning attacks against support vector machines (2012) https://arxiv.org/pdf/1206.6389.pdf

A. Saha, A. Subramanya, H. PirsiavashHidden trigger backdoor attacks Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, Menlo Park (2020), pp. 11957-11965

M.A. Rahman, T. Rahman, R. Laganière, N. Mohammed, Y. WangMembership inference attack against differentially private deep learning model Transactions on Data Privacy, 11 (1) (2018), pp. 61-79

M. Slaney, D. Naar, R. LyonAuditory model inversion for sound separation Proceedings of the ICASSP’94, IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE (1994), pp. II-77

P. Lahoti, K.P. Gummadi, G. WeikumiFair: Learning individually fair data representations for algorithmic decision making Proceedings of the 2019 IEEE 35th International Conference on Data Engineering (ICDE), IEEE (2019), pp. 1334-1345

A. BorjiA categorical archive of ChatGPT failures (2023) https://arxiv.org/pdf/2302.03494.pdf

B. Guo, X. Zhang, Z. Wang, M. Jiang, J. Nie, Y. Ding, J. Yue, Y. WuHow close is ChatGPT to human experts? Comparison corpus, evaluation, and detection (2023) https://arxiv.org/pdf/2301.07597.pdf

J. Pu, Z. Sarwar, S.M. Abdullah, A. Rehman, Y. Kim, P. Bhattacharya, M. Javed, B. ViswanathDeepfake text detection: Limitations and opportunities (2022) https://arxiv.org/pdf/2210.09421.pdf

Y. Tian, H. Chen, X. Wang, Z. Bai, Q. Zhang, R. Li, C. Xu, Y. WangMultiscale positive-unlabeled detection of AI-generated texts (2023) https://arxiv.org/pdf/2305.18149.pdf

I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. BengioGenerative adversarial networks Communications of the ACM, 63 (11) (2020), pp. 139-144

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据