As cyberattacks become more intelligent, it is challenging to detect advanced attacks in a variety of fields including industry, national defense, and healthcare. Traditional intrusion detection systems are no longer enough to detect these advanced attacks with unexpected patterns. Attackers bypass known signatures and pretend to be normal users. Deep learning is an alternative to solving these issues. Deep Learning (DL)-based intrusion detection does not require a lot of attack signatures or the list of normal behaviors to generate detection rules. DL defines intrusion features by itself through training empirical data. We develop a DL-based intrusion model especially focusing on denial of service (DoS) attacks. For the intrusion dataset, we use KDD CUP 1999 dataset (KDD), the most widely used dataset for the evaluation of intrusion detection systems (IDS). KDD consists of four types of attack categories, such as DoS, user to root (U2R), remote to local (R2L), and probing. Numerous KDD studies have been employing machine learning and classifying the dataset into the four categories or into two categories such as attack and benign. Rather than focusing on the broad categories, we focus on various attacks belonging to same category. Unlike other categories of KDD, the DoS category has enough samples for training each attack. In addition to KDD, we use CSE-CIC-IDS2018 which is the most up-to-date IDS dataset. CSE-CIC-IDS2018 consists of more advanced DoS attacks than that of KDD. In this work, we focus on the DoS category of both datasets and develop a DL model for DoS detection. We develop our model based on a Convolutional Neural Network (CNN) and evaluate its performance through comparison with an Recurrent Neural Network (RNN). Furthermore, we suggest the optimal CNN design for the better performance through numerous experiments.

한국멀티미디어학회(The Journal of Curriculum Evaluation)

As the number of Internet of Things (IoT) devices connected to the network rapidly increases, network attacks such as flooding and Denial of Service (DoS) are also increasing. These attacks cause network disruption and denial of service to IoT devices. However, a large number of heterogenous devices deployed in the IoT environment make it difficult to detect IoT attacks using traditional rule-based security solutions. It is challenging to develop optimal security models for each type of the device. Machine learning (ML) is an alternative technique that allows one to develop optimal security models based on empirical data from each device. We employ the ML technique for IoT attack detection. We focus on botnet attacks targeting various IoT devices and develop ML-based models for each type of device. We use the N-BaIoT dataset generated by injecting botnet attacks (Bashlite and Mirai) into various types of IoT devices, including a Doorbell, Baby Monitor, Security Camera, and Webcam. We develop a botnet detection model for each device using numerous ML models, including deep learning (DL) models. We then analyze the effective models with a high detection F1-score by carrying out multiclass classification, as well as binary classification, for each model.

Deepfake audio causes damage not only to individuals and companies, but also to nations; therefore, research on deepfake audio detection technology is crucial. Most existing deepfake audio detection research has been conducted using supervised learning; however, when a new synthetic deepfake audio emerges, real-time detection becomes difficult because of the limitations of supervised learning. Therefore, this paper proposes a new anomaly detection technique for identifying deep-fake audio using unsupervised learning. This method involves learning the feature distribution of numerous real human voices and then calculating an anomaly score for each voice to determine whether it is deepfake. In this study, we imaged speech using mel-spectrogram and mel-frequency cepstral coefficient (MFCC), which are speech preprocessing methods. Subsequently, the parameters of the GANomaly and f-AnoGAN models, which are effective in detecting abnormalities in speech, were tuned and subjected to unsupervised training. The most effective result had an F1-score of 0.93 in and was obtained by combining imaging speech with Mel-Spectrogram with training using the GANomaly model.

Spam detection is an essential and unavoidable problem in today’s society. Most of the existing studies have used string-based detection methods with models and have been conducted on a single language, especially with English datasets. However, in the current global society, research on languages other than English is needed. String-based spam detection methods perform different preprocessing steps depending on language type due to differences in grammatical characteristics. Therefore, our study proposes a text-processing method and a string-imaging method. The CNN 2D visualization technology used in this paper can be applied to datasets of various languages by processing the data as images, so they can be equally applied to languages other than English. In this study, English and Korean spam data were used. As a result of this study, the string-based detection models of RNN, LSTM, and CNN 1D showed average accuracies of 0.9871, 0.9906, and 0.9912, respectively. On the other hand, the CNN 2D image-based detection model was confirmed to have an average accuracy of 0.9957. Through this study, we present a solution that shows that image-based processing is more effective than string-based processing for string data and that multilingual processing is possible based on the CNN 2D model.