• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2627-2647
• /
• 2016

With the rapid growth of microblog, expert identification on microblog has been playing a crucial role in many applications. While most previous expert identification studies only assess global authoritativeness of a user, there is no way to differentiate the authoritativeness in a particular aspect of topics. In this paper, we propose a novel model, which jointly models text and following relationship in the same generative process. Furthermore, we integrate a similarity-based weight scheme into the model to address the popular bias problem, and use followee topic distribution as prior information to make user's topic distribution more precisely. Our empirical study on two large real-world datasets shows that our proposed model produces significantly higher quality results than the prior arts.

• Journal of IKEEE
• /
• v.2 no.1 s.2
• /
• pp.24-33
• /
• 1998

Independent Component analysis (ICA) is a new statistical method for extracting statistically independent components from their linear instantaneous mixtures which are generated by an unknown linear generative model. The recognition model is learned in unsupervised manner so that the recovered signals by the recognition model become the possibly scaled estimates of original source signals. This paper addresses the neural learning approach to ICA. As recognition models a linear feedforward network and a linear feedback network are considered. Associated learning algorithms for both networks are derived from maximum likelihood and information-theoretic approaches, using natural Riemannian gradient [1]. Theoretical results are confirmed by extensive computer simulations.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.104-107
• /
• 1996

This paper focuses on a automation selection of optimal cutting conditions and cycle time for multi-spindle metal cutting machines based on machining parameters and tool change schemes which are the two most common terms used in the metal cutting. In this research we used two step generative approach, step 1 is mathematical modeling for the selection fo optimal cutting conditions and the other is GMDH-Type modeling to estimate the system performance evaluation. We developed computer programs for these models and the fitting manufacturing examples are applied to this model and it was shown that the proposed approach has a good potential and offers a valuable tools to analyse the metal cutting system.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.2
• /
• pp.251-259
• /
• 2010

It is presented in this study a new efficient intelligent machining strategy, which can be used to remove the uncut volume at the boundary region of curved surfaces caused by cutter interference. The geometric form definitions and recognition of topological features of the surface triangulation mesh are used to generate cutter paths along successive and interconnected steepest pathways, that minimize the cusp height left after flat end milling. In order to machine the uncut volume gradually, the z-map cutter centers are adjusted to avoid cutter interference for the 6 kinds of avoidance types. And then, the generative subsequent paths are sequenced to determine the second step cutter paths for the next uncut volume. For the 2 kinds of test models with convex and concave surface region, the implemented software algorithm is evaluated by investigating the residual swelling of uncut volume for each machining step.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.3
• /
• pp.162-170
• /
• 2014

Appearance-based subspace models such as eigenfaces have been widely recognized as one of the most successful approaches to face recognition and tracking. The success of eigenfaces mainly has its origins in the benefits offered by principal component analysis (PCA), the representational power of the underlying generative process for high-dimensional noisy facial image data. The sparse extension of PCA (SPCA) has recently received significant attention in the research community. SPCA functions by imposing sparseness constraints on the eigenvectors, a technique that has been shown to yield more robust solutions in many applications. However, when SPCA is applied to facial images, the time and space complexity of PCA learning becomes a critical issue (e.g., real-time tracking). In this paper, we propose a very fast and scalable greedy forward selection algorithm for SPCA. Unlike a recent semidefinite program-relaxation method that suffers from complex optimization, our approach can process several thousands of data dimensions in reasonable time with little accuracy loss. The effectiveness of our proposed method was demonstrated on real-world face recognition and tracking datasets.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.942-945
• /
• 2019

현재 딥러닝은 컴퓨터 분야에서 이미지 처리 방법으로 활용도가 높아지면서 딥러닝 모델 개발 연구가 활발히 진행되고 있다. 딥러닝 모델 중에서 이미지 생성모델은 대표적으로 GAN(Generative Adversarial Network, 생성적 적대 신경망) 모델을 활용하고 있다. GAN은 생성기 네트워크와 판별기 네트워크를 이용하여 진짜 같은 이미지를 생성한다. 생성된 이미지는 실제 이미지와의 오차를 최소화해야 하며 이때 사용하는 함수를 손실함수라고 한다. GAN에서 손실함수는 이미지를 생성하는 학습이 불안정하여 이미지 품질이 떨어지는 문제가 있다. 개선된 GAN 관련 연구가 진행되고 있지만 완전한 문제 해결에는 부족하다. 본 논문은 7개의 GAN 모델에서 사용하는 손실함수를 분류하고 특징을 분석한다.

• Archives of Craniofacial Surgery
• /
• v.22 no.5
• /
• pp.223-231
• /
• 2021

The field of artificial intelligence (AI) is rapidly advancing, and AI models are increasingly applied in the medical field, especially in medical imaging, pathology, natural language processing, and biosignal analysis. On the basis of these advances, telemedicine, which allows people to receive medical services outside of hospitals or clinics, is also developing in many countries. The mechanisms of deep learning used in medical AI include convolutional neural networks, residual neural networks, and generative adversarial networks. Herein, we investigate the possibility of using these AI methods in the field of craniofacial surgery, with potential applications including craniofacial trauma, congenital anomalies, and cosmetic surgery.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.66-71
• /
• 2023

As cameras have become primary sensors for mobile robots, vision based Simultaneous Localization and Mapping (SLAM) has achieved impressive results with the recent development of computer vision and deep learning. However, vision information has a disadvantage in that a lot of information disappears in a low-light environment. To overcome the problem, we propose an image enhancement method to perform visual SLAM in a low-light environment. Using the deep generative adversarial models and modified gamma correction, the quality of low-light images were improved. The proposed method is less sharp than the existing method, but it can be applied to ORB-SLAM in real time by dramatically reducing the amount of computation. The experimental results were able to prove the validity of the proposed method by applying to public Dataset TUM and VIVID++.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.13-14
• /
• 2021

본 논문은 생성모델의 학습데이터 제작기법에 대한 실험 및 결과와 향후 관련 연구의 방향을 기술한다. GAN으로 대표되는 생성모델이 아티스트에게 얼마만큼의 만족도와 영감을 주는지를 비교 실험 및 평가하기 위해서는 정제된 학습데이터가 필요하다. 하지만 현실적으로 아티스트의 작품은 데이터 세트를 만들기에는 그 수가 적고 인공지능이 학습하기에도 정제되어있지 않다. 2차 가공작업을 통하여 아티스트의 원본 작업과 유사한 데이터 세트의 구축은 생성모델의 성능향상을 위해 매우 중요하다. 연구의 결과 생성모델이 표현하기 어려운 스타일의 작가 작품을 선정한 뒤 최적의 학습데이터를 만들기 위한 다양한 실험과 기법을 통해 구축한 데이터 세트를 생성모델 알고리즘에 적용하고 실험을 통해 창작자의 작품제작 의도인 작가 진술에 최대한 유사한 이미지의 생성과 더 나아가 작가가 생각하지 못했던 창조적 모방의 결과물을 도출하였고 작가평가를 통해 높은 만족도를 얻었다.