• ETRI Journal
• /
• v.39 no.5
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.338-345
• /
• 2024

Magnetic anomaly signals from the ferromagnetic targets such as ships in the sea are measured by drone-based magnetic anomaly detection. A quantum magnetometer is suspended from the drone by 4 strings. Flight altitude and speed of drone are 100 m and 5 m/s, respectively. We obtain magnetic anomaly signals of few nT from the ships clearly. We analyze the signal characteristics by the ferromagnetic target through simulation using COMSOL multiphysics.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.5
• /
• pp.99-106
• /
• 2011

In many applications, wireless sensor networks could be thought as data-centric networks, and the sensor nodes are densely distributed over a large sensor field. The sensor nodes are normally vulnerable in terms of security since they are very often deployed in a hostile environment and open space. In this paper, we propose a scheme for contents-based anomaly detection in wireless sensor networks. In this scheme we use the characteristics of sensor networks where several nodes surrounding an event point can simultaneously detect the phenomenon occurring and the contents detected from these sensors are limited to inside a certain range. The proposed scheme consists of several phases; training, testing and refining phases. Anomaly candidates detected by the distance-based anomaly detection scheme in the testing phase are sent to the refining phase. They are then compared in the sink node with previously collected data set to improve detection performance in the refining phase. Our simulation results suggest the effectiveness of the proposed scheme in this paper evidenced by the improvements of the detection rate and the false positive rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.4
• /
• pp.647-660
• /
• 2022

Recent works demonstrate that the semi-supervised anomaly detection method functions quite well in the environment with normal data and some anomalous data. However, abnormal data shortages can occur in an environment where it is difficult to reserve anomalous data, such as an unknown attack in the cyber security fields. In this paper, we propose ADA-PH(Abnormal Data Augmentation Method using Perturbation based on Hypersphere), a novel anomalous data augmentation method that is applicable in an environment where abnormal data is insufficient to secure the performance of the semi-supervised anomaly detection method. ADA-PH generates abnormal data by perturbing samples located relatively far from the center of the hypersphere. With the network intrusion detection datasets where abnormal data is rare, ADA-PH shows 23.63% higher AUC performance than anomaly detection without data augmentation and even performs better than the other augmentation methods. Also, we further conduct quantitative and qualitative analysis on whether generated abnormal data is anomalous.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1516-1529
• /
• 2023

In this paper, a motor gearbox fault-detection system based on a hierarchical flow-based model is proposed. The proposed system is used for the anomaly detection of a motion sound-based actuator module. The proposed flow-based model, which is a generative model, learns by directly modeling a data distribution function. As the objective function is the maximum likelihood value of the input data, the training is stable and simple to use for anomaly detection. The operation sound of a car's side-view mirror motor is converted into a Mel-spectrogram image, consisting of a folding signal and an unfolding signal, and used as training data in this experiment. The proposed system is composed of an encoder and a decoder. The data extracted from the layer of the pretrained feature extractor are used as the decoder input data in the encoder. This information is used in the decoder by performing an interlayer cross-scale convolution operation. The experimental results indicate that the context information of various dimensions extracted from the interlayer hierarchical data improves the defect detection accuracy. This paper is notable because it uses acoustic data and a normalizing flow model to detect outliers based on the features of experimental data.

• Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
• /
• v.12 no.6
• /
• pp.579-590
• /
• 2018

Anomaly detection on building energy consumption has been regarded as an effective tool to reduce energy saving on building operation and maintenance. However, it requires energy model and FDD expert for quantitative model approach or large amount of training data for qualitative/history data approach. Both method needs additional time and labors. This study propose a machine learning and data science approach to define faulty conditions on hourly building energy consumption with reducing data amount and input requirement. It suggests an application of Support Vector Data Description (SVDD) method on training normal condition of hourly building energy consumption incorporated with hourly outdoor air temperature and time integer in a week, 168 data points and identifying hourly abnormal condition in the next day. The result shows the developed model has a better performance when the ${\nu}$ (probability of error in the training set) is 0.05 and ${\gamma}$ (radius of hyper plane) 0.2. The model accuracy to identify anomaly operation ranges from 70% (10% increase anomaly) to 95% (20% decrease anomaly) for daily total (24 hours) and from 80% (10% decrease anomaly) to 10%(15% increase anomaly) for occupied hours, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.301-304
• /
• 2005

For detecting an intrusion based on the anomaly of a user's activities, previous works are concentrated on statistical techniques or frequent episode mining in order to analyze an audit data. But, since they mainly analyze the average behaviour of user's activities, some anomalies can be detected inaccurately. Therefore, we propose an anomaly detection method that utilizes an associative classification for modelling intrusion detection. Finally, we proof that a prediction model built from associative classification method yields better accuracy than a prediction model built from a traditional methods by experimental results.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.315-326
• /
• 2007

The rapid proliferation of wireless networks and mobile computing applications has changed the landscape of network security. Anomaly detection is a pattern recognition task whose goal is to report the occurrence of abnormal or unknown behavior in a given system being monitored. This paper presents a dynamic anomaly detection scheme that can effectively identify a group of especially harmful internal masqueraders in cellular mobile networks. Our scheme uses the trace data of wireless application layer by a user as feature value. Based on the feature values, the use pattern of a mobile's user can be captured by rough sets, and the abnormal behavior of the mobile can be also detected effectively by applying a roughness membership function with both the age of the user profile and weighted feature values. The performance of our scheme is evaluated by a simulation. Simulation results demonstrate that the anomalies are well detected by the proposed dynamic scheme that considers the age of user profiles.