Digital Library[ Search Result ]
Adaptive Database Intrusion Detection based on Michigan-style Deep Learning Classifier System
http://doi.org/10.5626/JOK.2023.50.10.891
In a role-based access control (RBAC) environment, database intrusion detection can be achieved by designing a role classifier for query transactions and determining it as an intrusion when the predicted role differs from the actually performed role. The current query-role classifier design methods utilize deep learning models, but it was difficult to simultaneously achieve high accuracy and incomplete adaptability for changing patterns. To solve this problem, this study proposes a Michigan-style Deep Learning Classifier System (MDLCS). This method applies a divide-and-conquer strategy that divides the input space into patterns and assigns an optimal classifier, combining the evolutionary computation principle of a Michigan-style learning classifier system with a deep learning classifier to adapt and improve detection performance for real-time changing patterns.The proposed MDLCS method provides strong adaptability and robustness compared to existing intrusion detection methods such as anomaly detection, signature-based detection and behavior-based detection. MDLCS was evaluated in a commercial database following the TPC-E schema and achieved a 26.81%p improved detection performance compared to existing methods under real environmental conditions in which new patterns sequentially emerge.
Learning Functional Characteristics of Malware Attacks with Graph Transformer based on Control Flow
http://doi.org/10.5626/JOK.2023.50.8.633
To minimize false negatives in malware classification, it is important to capture local characteristics of a program, such as the control flow between operation blocks and memory-register addresses. However, existing methods that optimize the loss function of a classifier without considering the functional characteristics of malware have limitations in recall due to new attack paths and complex control flow graphs. In this paper, we propose a method that explicitly samples and embeds the control flow graphs to learn functional characteristics, such as API calls, rootkit DLL installation, and specific virtual memory access, and improve recall. To model the functional patterns of malware from the control flow graphs, we sample attack paths from the control flow of the malware and classify the types of malware using a graph embedding function based on the transformer. We evaluate the proposed method using a real-world malware benchmark dataset, Microsoft Challenge. By explicitly learning the control flow of the malware, we achieved a recall of 97.89% and significantly improved the accuracy (99.45%) compared to the latest and most advanced method"s classification accuracy (97.89%).
Integrating Domain Knowledge with Graph Convolution based on a Semantic Network for Elderly Depression Prediction
Seok-Jun Bu, Kyoung-Won Park, Sung-Bae Cho
http://doi.org/10.5626/JOK.2023.50.3.243
Depression in the elderly is a global problem that causes 300 million patients and 800,000 suicides every year, so it is critical to detect early daily activity patterns closely related to mobility. Although a graph-convolution neural network based on sensing logs has been promising, it is required to represent high-level behaviors extracted from complex sensing information sequences. In this paper, a semantic network that structuralizes the daily activity patterns of the elderly was constructed using additional domain knowledge, and a graph convolution model was proposed for complementary uses of low-level sensing log graphs. Cross-validation with 800 hours of data from 69 senior citizens provided by DNX, Inc. revealed improved prediction performance for the suggested strategy compared to the most recent deep learning model. In particular, the inference of a semantic network was justified by a graph convolution model by showing a performance improvement of 28.86% compared with the conventional model.
A Cross Domain Adaptation Method based on Adversarial Cycle Consistence Learning for Rotary Machine Fault Diagnosis
http://doi.org/10.5626/JOK.2022.49.7.530
Research on data-based fault diagnosis models is being actively conducted in various industries. However, in the case of industrial equipment, various operating conditions occur, and it is difficult to secure sufficient training data. To solve this problem, a cross-domain adaptation technique can be utilized. In this study, we propose an adversarial consistency-maintaining transformation learning method that can maintain failure classification consistency even for the new untrained environmental data using the rotating body vibration data. The data generated through consistent learning creates a continuous invariant latent space between the new operating condition data distribution and the known data distribution and learns to maintain the failure classification performance through an adversarial learning network that shares the failure classification characteristic information. Therefore, the proposed method can provide a more stable and general classification performance by expanding the potential space to minimize the discrepancy between domain data. The experimental results of the proposed model showed about 88% accuracy for a real-machine dataset, and compared to the existing cross-domain adaptive learning methods, it showed a performance improvement of about 5-10%. According to the results of this study, it is expected to be an effective solution for the problem of equipment failure diagnosis at actual industrial sites.
An Autism Spectrum Disorder Detection System Based on Learning Dynamic Connectivity of the Superior Temporal Sulcus
Kyoung-Won Park, Seok-Jun Bu, Sung-Bae Cho
http://doi.org/10.5626/JOK.2022.49.5.354
Considering a hypothesis that abnormalities in the superior temporal sulcus (STS) connected with visual cortex regions can be a critical sign of ASD, autism spectrum disorder, a model is required to exploit the brain functional connectivity between the STS and visual cortex to reinforce the neurobiological evidence. This paper proposes a deep learning model comprising attention and convolutional recurrent neural networks that can select and extract the time-series pattern of dynamic connectivity between the two regions within the brain based on observations. By integration of the extracted autism disorder features from dynamic connectivity through attention with the structure containing interlayer connections to preserve the functional connectivity loss within a neural network, the model extracts the connectivity between the STS and visual cortex, leading to an increase in generalization performance. A 10-fold cross-validation to compare the performance shows that the proposed model outperforms the state-of-the-art models by achieving an improvement of 4.90% in the ASD classification. Additionally, we use the proposed method to diagnose ASD by visualizing dynamic brain connectivity of the neural network layers.
Generative Adversarial Networks Using Pre-trained Generator for Effective Auditory Noise Suppression
http://doi.org/10.5626/JOK.2021.48.3.334
Speech enhancement GAN (SEGAN) is one of the models showing good performance in removing acoustic noise based on the genrative adversarial network, which is one of the deep learning models. However, there is a problem that the generator is easily unstable while learning non-stationary noise with a very wide distribution with one genrator. In this paper, to improve this problem, we propose an adversarial learning method using a pre-trained generator. The output of the learned generator in the same way as the autoencoder is used as the input of the adversarial learning generator. It improve stability and alleviate the difficulty of the problem, through the primary reduced noisy signal. In this paper, the Scale Invariant Signal to Noise Ratio (SI-SNR) evaluation index was used to objectively evaluate the performance of the model. As a result of the experiment, the SI-SNR increased by about 4.08 compared to the noisy speech, confirming that the proposed method is useful for removing noise.
Pattern Extraction from Lifelog Based on Semantic Network Structure Using Petri-Net
http://doi.org/10.5626/JOK.2020.47.6.553
Recently, with the spread of smart devices, the user’s lifelog data is automatically stored through various types of sensors. But the lifelog collected from smart devices records heterogeneous information from different sensors. In addition, since the user"s life patterns are determined by different judgment cycles, it is difficult to express them in a simple rule-based system. Therefore, in order to extract and provide useful life patterns for users from the lifelog, it is necessary to express the relationship of numerous dynamic elements. In this paper, we propose a method to automatically extract user life patterns using Petri-nets from the lifelog represented by the semantic network. Petri-net reduces the uncertainty in smart device sensor data and increases the diversity of life patterns. The proposed life pattern extraction method is structured by the semantic network to represent the semantic relationship of heterogeneously collected user lifelog. Also, the Petri-net graph automatically determines the lifelog and then extracts individual sleep and eating patterns.
Deep Learning Model based on Autoencoder for Reducing Algorithmic Bias of Gender
http://doi.org/10.5626/JOK.2019.46.8.721
Algorithmic bias is a discrimination that is reflected in the model by a bias in data or combination of characteristics of model and data in the algorithm. In recent years, it has been identified that the bias is not only present but also amplified in the deep learning model; thus, there exists a problem related to bias elimination. In this paper, we analyze the bias of the algorithm by gender in terms of bias-variance dilemma and identify the cause of bias. To solve this problem, we propose a deep auto-encoder based latent space matching model. Based on the experimental results, it is apparent that the algorithm bias in deep learning is caused by difference of the latent space for each protected feature in the feature extraction part of the model. A model proposed in this paper achieves the low bias by reducing the differences in extracted features by transferring data with different gender characteristics to the same latent space. We employed Equality of Odds and Equality of Opportunity as a quantitative measure and proved that proposed model is less biased than the previous model. The ROC curve shows a decrease in the deviation of the predicted values between the genders.
A Transfer Learning Method for Solving Imbalance Data of Abusive Sentence Classification
http://doi.org/10.5626/JOK.2017.44.12.1275
The supervised learning approach is suitable for classification of insulting sentences, but pre-decided training sentences are necessary. Since a Character-level Convolution Neural Network is robust for each character, so is appropriate for classifying abusive sentences, however, has a drawback that demanding a lot of training sentences. In this paper, we propose transfer learning method that reusing the trained filters in the real classification process after the filters get the characteristics of offensive words by generated abusive/normal pair of sentences. We got higher performances of the classifier by decreasing the effects of data shortage and class imbalance. We executed experiments and evaluations for three datasets and got higher F1-score of character-level CNN classifier when applying transfer learning in all datasets.
Group Emotion Prediction System based on Modular Bayesian Networks
http://doi.org/10.5626/JOK.2017.44.11.1149
Recently, with the development of communication technology, it has become possible to collect various sensor data that indicate the environmental stimuli within a space. In this paper, we propose a group emotion prediction system using a modular Bayesian network that was designed considering the psychological impact of environmental stimuli. A Bayesian network can compensate for the uncertain and incomplete characteristics of the sensor data by the probabilistic consideration of the evidence for reasoning. Also, modularizing the Bayesian network has enabled flexible response and efficient reasoning of environmental stimulus fluctuations within the space. To verify the performance of the system, we predict public emotion based on the brightness, volume, temperature, humidity, color temperature, sound, smell, and group emotion data collected in a kindergarten. Experimental results show that the accuracy of the proposed method is 85% greater than that of other classification methods. Using quantitative and qualitative analyses, we explore the possibilities and limitations of probabilistic methodology for predicting group emotion.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr