한국어 악성 프롬프트 주입 공격을 통한 거대 언어 모델의 유해 표현 유도
Vol. 34, No. 3, pp. 451-461,
6월.
2024
10.13089/JKIISC.2024.34.3.451,
Full Text:
Keywords: Generative AI, Large Languge Model (LLM), Prompt Injection Attack, Harmful Speech
Abstract Statistics
Cite this article
![](https://d2kjln74dkk4oj.cloudfront.net/img/doi_icon.png)
![](https://d2kjln74dkk4oj.cloudfront.net/img/pdficon_small.png)
Keywords: Generative AI, Large Languge Model (LLM), Prompt Injection Attack, Harmful Speech
Abstract Statistics
Cite this article
[IEEE Style]
서지민 and 김진우, "Inducing Harmful Speech in Large Language Models through Korean Malicious Prompt Injection Attacks," Journal of The Korea Institute of Information Security and Cryptology, vol. 34, no. 3, pp. 451-461, 2024. DOI: 10.13089/JKIISC.2024.34.3.451.
[ACM Style]
서지민 and 김진우. 2024. Inducing Harmful Speech in Large Language Models through Korean Malicious Prompt Injection Attacks. Journal of The Korea Institute of Information Security and Cryptology, 34, 3, (2024), 451-461. DOI: 10.13089/JKIISC.2024.34.3.451.