• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.451-461
• /
• 2024

Recently, various AI chatbots based on large language models have been released. Chatbots have the advantage of providing users with quick and easy information through interactive prompts, making them useful in various fields such as question answering, writing, and programming. However, a vulnerability in chatbots called "prompt injection attacks" has been proposed. This attack involves injecting instructions into the chatbot to violate predefined guidelines. Such attacks can be critical as they may lead to the leakage of confidential information within large language models or trigger other malicious activities. However, the vulnerability of Korean prompts has not been adequately validated. Therefore, in this paper, we aim to generate malicious Korean prompts and perform attacks on the popular chatbot to analyze their feasibility. To achieve this, we propose a system that automatically generates malicious Korean prompts by analyzing existing prompt injection attacks. Specifically, we focus on generating malicious prompts that induce harmful expressions from large language models and validate their effectiveness in practice.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.225-230
• /
• 2020

This paper highlights the influence and the importance of the syntactic-grammatical knowledge on "the reading machine", appeared in Jackendoff (1999). Due to the lack of the detailed testing and implementation in his research, this paper tests an extensive data array using a component of Google Translate, currently available freely and most widely on the internet. Although outdated, Jackendoff's paper, "Why can't Computers use English?", argues that syntactic-grammatical knowledge plays a key role in the outputs of computers and computer-based reading machines. The current research has implemented some testings of his thought-provoking examples, in order to find out whether Google Translate can handle the same problems after two decades or so. As a result, it is argued that in the field of NLP, I-language in the sense of Chomsky (1986, 1995 etc) is real and the syntactic, grammatical, and categorial knowledge is essential in the faculty of language. Therefore, it is reassured in this paper that when it comes to human language, even the most advanced "machine" is still no match for human faculty of language, the syntactic-grammatical knowledge.

• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.19-47
• /
• 2024

Organizational ability to analyze and utilize data plays an important role in knowledge management and decision-making. This study aims to investigate the potential application of large language models in corporate data analysis. Focusing on the field of human resources, the research examines the data analysis capabilities of these models. Using the widely studied IBM HR dataset, the study reproduces machine learning-based employee turnover prediction analyses from previous research through ChatGPT and compares its predictive performance. Unlike past research methods that required advanced programming skills, ChatGPT-based machine learning data analysis, conducted through the analyst's natural language requests, offers the advantages of being much easier and faster. Moreover, its prediction accuracy was found to be competitive compared to previous studies. This suggests that large language models could serve as effective and practical alternatives in the field of corporate data analysis, which has traditionally demanded advanced programming capabilities. Furthermore, this approach is expected to contribute to the popularization of data analysis and the spread of data-driven decision-making (DDDM). The prompts used during the data analysis process and the program code generated by ChatGPT are also included in the appendix for verification, providing a foundation for future data analysis research using large language models.

• Journal of The Korean Association of Information Education
• /
• v.12 no.1
• /
• pp.77-88
• /
• 2008

A programming education has favorable influence on creative / logical thinking and problem solving ability of students. However, students typically have to spend too much effort in learning basic grammar and the usage model of programming languages, which negatively affect their eagerness in learning. In this respect, we proposed to apply the 'Scratch' using the Creative Problem Solving(CPS) Teaching Model; Scratch is an easy-to-learn and intuitive Educational Programming Language(EPL) that helps improving the problem solving ability of the class. Then we verified the effect of Scratch EPL through the design of both pretest and posttest for a subject group. In summary, the CPS based Scratch EPL was shown to significantly improve the problem solving ability and also help them develop favorable attitude in programming.

• Journal of Digital Convergence
• /
• v.14 no.7
• /
• pp.363-371
• /
• 2016

Technology evaluation for technology innovation of venture firms should take the rapidly changing corporate environment, the ambiguity of language used in evaluation, and the inaccuracy of evaluation index into consideration. In this paper, targeting the absorptive capacity and technological entrepreneurship which are typical evaluation factors of venture firms, an ACTEM model to calculate the importance, priority, and dynamic capability of factors, applying Fuzzy-AHP was proposed. The fuzzy theory was introduced to compensate for the ambiguity of cognitive judgments when calculating weighted values for the factors that made up an assessment scale. An assessment criteria framework for absorptive capacity, technological entrepreneurship, and dynamic capability, which were not considered in previous studies on the evaluation and measurement of technological prowess, so that the users could have a realistic alternative to choose. The study compared the ACTEM model with the old AHP assessment method and found that "knowledge acquisition" and "producing ability" were the highest in absorptive capacity and technological entrepreneurship, respectively, thus demonstrating its validity.

• Annual Conference on Human and Language Technology
• /
• 1999.10e
• /
• pp.7-12
• /
• 1999

정보 검색 시스템은 사용자 질의의 키워드들과 문서들의 유사성(similarity)을 기준으로 관련 문서들을 순서화하여 사용자에게 제공한다. 그렇지만 인터넷 검색에 사용되는 질의는 일반적으로 짧기 때문에 보다 유용한 질의를 만들고자 하는 노력이 지금까지 계속되고 있다. 그러나 키워드에 포함된 정보가 제한적이기 때문에 이에 대한 보완책으로 사용자의 적합성 피드백을 이용하는 방법을 널리 사용하고 있다. 본 논문에서는 일반적인 적합성 피드백의 가장 큰 단점인 빈번한 사용자 참여는 지양하고, 시스템에 기반한 적합성 피드백에서 배제한 사용자 참여를 유도하는 검색 문서의 분류 정보에 기반한 용어 클러스터 질의 확장 모델(Term Cluster Query Expansion Model)을 제안한다. 이 방법은 검색 시스템에 의해 검색된 상위 n개의 문서에 대하여 분류기를 이용하여 각각의 문서에 분류 정보를 부여하고, 문서에 부여된 분류 정보를 이용하여 분류 정보의 수(m)만큼으로 문서들을 그룹을 짓는다. 적합성 피드백 알고리즘을 이용하여 m개의 그룹으로부터 각각의 용어 클러스터(Term Cluster)를 생성한다. 이 클러스터가 사용자에게 문서 대신에 피드백의 자료로 제공된다. 실험 결과, 적합성 알고리즘 중 Rocchio방법을 이용할 때 초기 질의보다 나은 성능을 보였지만, 다른 연구에서 보여준 성능 향상은 나타내지 못했다. 그 이유는 분류기의 오류와 문서의 특성상 한 영역으로 규정짓기 어려운 문서가 존재하기 때문이다. 그러나 검색하고자 하는 사용자의 관심 분야나 찾고자 하는 성향이 다르더라도 시스템에 종속되지 않고 유연하게 대처하며 검색 성능(retrieval effectiveness)을 향상시킬 수 있다.사용되고 있어 적응에 문제점을 가지기도 하였다. 본 연구에서는 그 동안 계속되어 온 한글과 한잔의 사용에 관한 논쟁을 언어심리학적인 연구 방법을 통해 조사하였다. 즉, 글을 읽는 속도, 글의 의미를 얼마나 정확하게 이해했는지, 어느 것이 더 기억에 오래 남는지를 측정하여 어느 쪽의 입장이 옮은 지를 판단하는 것이다. 실험 결과는 문장을 읽는 시간에서는 한글 전용문인 경우에 월등히 빨랐다. 그러나. 내용에 대한 기억 검사에서는 국한 혼용 조건에서 더 우수하였다. 반면에, 이해력 검사에서는 천장 효과(Ceiling effect)로 두 조건간에 차이가 없었다. 따라서, 본 실험 결과에 따르면, 글의 읽기 속도가 중요한 문서에서는 한글 전용이 좋은 반면에 글의 내용 기억이 강조되는 경우에는 한자를 혼용하는 것이 더 효율적이다.이 높은 활성을 보였다. 7. 이상을 종합하여 볼 때 고구마 끝순에는 페놀화합물이 다량 함유되어 있어 높은 항산화 활성을 가지며, 아질산염소거능 및 ACE저해활성과 같은 생리적 효과도 높아 기능성 채소로 이용하기에 충분한 가치가 있다고 판단된다.등의 관련 질환의 예방, 치료용 의약품 개발과 기능성 식품에 효과적으로 이용될 수 있음을 시사한다.tall fescue 23%, Kentucky bluegrass 6%, perennial ryegrass 8%) 및 white clover 23%를 유지하였다. 이상의 결과를 종합할 때, 초종과 파종비율에 따른 혼파초지의 건물수량과 사료가치의 차이를 확인할 수 있었으며, 레드 클로버 + 혼파 초지가 건물수량과 사료가치를 높이는데 효과적이었다.\ell}$ 이었으며 , yeast extract 첨가(添加)하여 배양시(培養時)는 yeast extract

• Journal of Internet Computing and Services
• /
• v.5 no.6
• /
• pp.121-128
• /
• 2004

This paper proposes a quality evaluation system of a handwriting string written by electronic pen. For the purpose of the system, this paper describes how to retrieve reference data from a database, how to evaluate the quality of a handwiting string using global and local features. Also, it explains how to optionally recognize a grade of a handwriting string at using global and how to diagnose stroke order at using local. The quality can be evaluated in the case of different language between reference and input by the system. Therefore, we expect that the system is very useful not only for training on handwriting but also for learning a language.

• Journal of the Korean earth science society
• /
• v.31 no.7
• /
• pp.785-797
• /
• 2010

This study identified the linguistic features of Earth science treatises through the analysis of the register. Data included three Korean treatises that were in geology, atmospheric science, and oceanography. The register of Earth science treatise was as follows: First, there were semantic, referential connections between Themes and Rhemes, that the messages and main points of the texts were expressed coherently and cohesively. Second, some predicates were used which were related to deductive inference, abductive inferences, or causal relation according to the genre elements of each text. The logical relations were not represented by the conjunctions but by the types of predicates. Third, most texts in the treatises showed interpersonally weak relationship using mental predicates related to possibilities, which meant scientists expressed indirectly their interpretation, explanation, or arguments. From these results, we argued that some activities of unpacking the language of science be included in science curriculum in order to improve students' literacy of science texts and understanding scientists' knowledge construction.

• Design Convergence Study
• /
• v.13 no.2
• /
• pp.143-164
• /
• 2014

In this study, we suggest a tablet-PC based application as an instrument for self-examination of dementia and aim to evaluate its usability for the practical use. The tool for the self-diagnosis of dementia is testing a person's sentence comprehension, which is investigated by the accuracy of a sentence-picture matching task, and the result of the test can differentiate individuals with dementia of Alzheimer's type from normal aging population. According to its use for diagnosis of dementia, we developed a new version of sentence-picture matching task by a cooperative study with NABLE(Neurogenic communication And Brain Lab at Ewha) and applied to the application as a main function. Targeting the New Silver who are preliminary aged people in Korea, this application can provide them with three values: 'self-', 'easy', and 'simple'. When using this application, users can gain these values by an instruction manual with the recorded guide voice, easy-to-use functions and the simplified menu structure of it. After prototyping, we conducted the usability test and it was proved as a result that the New Silver users can easily operate the application by themselves.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.230-234
• /
• 1999

Inheritance and concurrency are the primary feature of object oriented languages, and are especially important for code re-use. They provide maximum computational power and modeling power through concurrency of objects. But, concurrent objects and inheritance have conflicting characteristics, thereby simultaneously use of them causes the problem, so failed inheritance anomaly, which requires code redefinition of inherited methods to maintain integrity of objects. In this paper, to solve the inheritance anomaly problems we introduce concept of state abstraction, in which infernal states of encapsulated objects are made available from a part of object's external interface. And we design inheritance interface mechanisms which methods are inherited efficiently. In our scheme, we can solve the typical inheritance anomaly problems.