• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2023

Convolutional neural networks have already been applied to various fields beyond human visual processing capabilities in the image processing area. However, they are exposed to a severe risk of deteriorating model performance due to the appearance of adversarial attacks. In addition, defense technology to respond to adversarial attacks is effective against the attack but is vulnerable to other types of attacks. Therefore, to respond to an adversarial attack, it is necessary to analyze how the performance of the adversarial attack deteriorates through the process inside the convolutional neural network. In this study, the adversarial attack of the Alexnet and VGG11 models was analyzed using the population sparseness index, a measure of neuronal activity in neurophysiology. Through the research, it was observed in each layer that the population sparsity index for adversarial examples showed differences from that of benign examples.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2A
• /
• pp.131-143
• /
• 2009

Under transverse earthquake shaking, arching action of bridge structures develops along the deck between the abutments thus providing the so-called deck resistance. The magnitude of the arching action for bridge structures is dependent on the number of spans, connection condition between deck and abutment or piers, and stiffness ratio between superstructure and substructure. In order to investigate the arching action effects for inelastic seismic responses of PSC Box bridges, seismic responses evaluated by pushover analysis, capacity spectrum analysis and nonlinear time-history analysis are compared for 18 example bridge structures with two types of span numbers (short bridge, SB and long bridge, LB), three types of pier height arrangement (regular, semi-regular and irregular) and three types of connection condition between superstructure and substructure (Type A, B, C). The arching action effects (reducing inelastic displacement and increasing resistance capacity) for short bridge (SB) is more significant than those for long bridge (LB). Semi-regular and irregular bridge structures have more significant arching action than regular bridges.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.61-69
• /
• 2009

This paper presents an improved method measuring inter-utterance similarity in an example-based dialogue system, which searches the most similar utterance in a dialogue database to generate a response to a given user utterance. Unlike general inter-sentence similarity measures, the inter-utterance similarity measure for example-based dialogue system should consider not only word distribution but also various linguistic features, such as affirmation/negation, tense, modality, sentence type, which affects the natural conversation. However, previous approaches do not sufficiently reflect these features. This paper proposes a new utterance similarity measure by analyzing and reflecting various linguistic features to improve performance in accuracy. Also, by considering substitutability of the features, the proposed method can utilize limited number of examples. Experimental results show that the proposed method achieves 10%p improvement in accuracy compared to the previous method.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.1-9
• /
• 2024

Although federated learning is designed to be safer than centralized methods in terms of security and privacy, it still has many vulnerabilities. An attacker performing an adversarial attack intentionally manipulates the deep learning model by injecting carefully crafted input data, that is, adversarial examples, into the client's training data to induce misclassification. A common defense strategy against this is so-called adversarial training, which involves preemptively learning the characteristics of adversarial examples into the model. Existing research assumes a scenario where all clients are under adversarial attack, but considering the number of clients in federated learning is very large, this is far from reality. In this paper, we experimentally examine aspects of adversarial training in a scenario where some of the clients are under attack. Through experiments, we found that there is a trade-off relationship in which the classification accuracy for normal samples decreases as the classification accuracy for adversarial examples increases. In order to effectively utilize this trade-off relationship, we present a method to perform adversarial training by adaptively selecting a loss function depending on whether the client is attacked.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.43-51
• /
• 2006

This paper proposes a metrics for example matching under the example-based machine translation for English-Korean machine translation. Our metrics served as similarity measure is based on edit-distance algorithm, and it is employed to retrieve the most similar example sentences to a given query. Basically it makes use of simple information such as lemma and part-of-speech information of typographically mismatched words. Edit-distance algorithm cannot fully reflect the context of matched word units. In other words, only if matched word units are ordered, it is considered that the contribution of full matching context to similarity is identical to that of partial matching context for the sequence of words in which mismatching word units are intervened. To overcome this drawback, we propose the context-weighting scheme that uses the contiguity information of matched word units to catch the full context. To change the edit-distance metrics representing dissimilarity to similarity metrics, to apply this context-weighted metrics to the example matching problem and also to rank by similarity, we normalize it. In addition, we generalize previous methods using some linguistic information to one representative system. In order to verify the correctness of the proposed context-weighted metrics, we carry out the experiment to compare it with generalized previous methods.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.439-444
• /
• 2008

The techniques, which locate example motions in abstract parameter space and interpolate them to generate new motion with given parameters, are widely used in real-time animation system for its controllability and efficiency However, as the dimension of parameter space increases for more complex control, the number of example motions for parameterization increases exponentially. This paper proposes a method that uses two different parameter spaces to obtain decoupled control over upper-body and lower-body motion. At each frame time, each parameterized motion space produces a source frame, which satisfies the constraints involving the corresponding body part. Then, the target frame is synthesized by splicing the upper body of one source frame onto the lower body of the other. To generate corresponding source frames to each other, we present a novel scheme for time-warping. This decoupled parameterization alleviates the problems caused by dimensional complexity of the parameter space and provides users with layered control over the character. However, when the examples are parameterized based on their upper body's spatial properties, the parameters of the examples are varied individually with every change of its lower body. To handle this, we provide an approximation technique to change the positions of the examples rapidly in the parameter space.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.194-199
• /
• 2022

Preprocessing for high-quality data is required for high accuracy and usability in various and complex image data-based industries. However, when a contaminated hostile example that combines noise with existing image or video data is introduced, which can pose a great risk to the company, it is necessary to restore the previous damage to ensure the company's reliability, security, and complete results. As a countermeasure for this, restoration was previously performed using Defense-GAN, but there were disadvantages such as long learning time and low quality of the restoration. In order to improve this, this paper proposes a method using adversarial examples created through FGSM according to image segmentation in addition to using the VQ-VAE model. First, the generated examples are classified as a general classifier. Next, the unsegmented data is put into the pre-trained VQ-VAE model, restored, and then classified with a classifier. Finally, the data divided into quadrants is put into the 4-split-VQ-VAE model, the reconstructed fragments are combined, and then put into the classifier. Finally, after comparing the restored results and accuracy, the performance is analyzed according to the order of combining the two models according to whether or not they are split.

• ICROS
• /
• v.4 no.1
• /
• pp.28-32
• /
• 1998

본 글에서는 실시간 분산처리 제어기를 위한 시뮬레이터의 구조를 제시한다. 분산처리 환경에서 각각의 노드 간에 비주기적으로 발생하는 메시지와 주기적으로 발생하는 데이터의 교환을 위한 통신 구조와 가상머신을 이용한 객체지향형 시뮬레이터 구조를 제시하고자 한다. 그리고 제안된 구조의 소프트웨어를 이용하여 PID 제어기를 설계하는 예제를 보여준다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.183-187
• /
• 2000

본 논문에서는 불확실성을 가지는 TS 퍼지 시스템을 안정화시킬 수 있는 제어기를 제안하고, 선형행렬부등식(Linear Matrix Inequality : LMI)을 이용한 설계 방법을 제시하였다. 그리고, 간단한 예제를 통하여 제안된 기법의 응용 가능성을 확인하여 보았다.

• Journal of the KSME
• /
• v.43 no.12
• /
• pp.42-46
• /
• 2003

이 글에서는 JAVA 언어를 이용한 인터넷 실험 실습 교육에 대하여 소개하고자 한다. 저자는 영남대학교 기계공학부의 실험 실습 교육 아이템 30여 개를 JAVA를 이용한 가상실험으로 개발한 바 있을 뿐만 아니라, 수치해석 강의나 열전달, 유체역학 등에서 기본적인 개념이나 수치모사에 의한 예제 등을 JAVA를 이용한 프로그램으로 개발하여 교육에 활용한 바 있어 이를 토대로 느낀 바를 이어가고자 한다.