Clustering Approach for Detecting Multiple Types of Adversarial Examples.

With intentional feature perturbations to a deep learning model, the adversary generates an adversarial example to deceive the deep learning model. As an adversarial example has recently been considered in the most severe problem of deep learning technology, its defense methods have been actively studied. Such effective defense methods against adversarial examples are categorized into one of the three architectures: (1) model retraining architecture; (2) input transformation architecture; and (3) adversarial example detection architecture. Especially, defense methods using adversarial example detection architecture have been actively studied. This is because defense methods using adversarial example detection architecture do not make wrong decisions for the legitimate input data while others do. In this paper, we note that current defense methods using adversarial example detection architecture can classify the input data into only either a legitimate one or an adversarial one. That is, the current defense methods using adversarial example detection architecture can only detect the adversarial examples and cannot classify the input data into multiple classes of data, i.e., legitimate input data and various types of adversarial examples. To classify the input data into multiple classes of data while increasing the accuracy of the clustering model, we propose an advanced defense method using adversarial example detection architecture, which extracts the key features from the input data and feeds the extracted features into a clustering model. From the experimental results under various application datasets, we show that the proposed method can detect the adversarial examples while classifying the types of adversarial examples. We also show that the accuracy of the proposed method outperforms the accuracy of recent defense methods using adversarial example detection architecture.

Robust Indoor Localization Methods Using Random Forest-Based Filter against MAC Spoofing Attack.

With the development of wireless networks and mobile devices, interest on indoor localization systems (ILSs) has increased. In particular, Wi-Fi-based ILSs are widely used because of the good prediction accuracy without additional hardware. However, as the prediction accuracy decreases in environments with natural noise, some studies were conducted to remove it. So far, two representative methods, i.e., the filtering-based method and deep learning-based method, have shown a significant effect in removing natural noise. However, the prediction accuracy of these methods severely decreased under artificial noise caused by adversaries. In this paper, we introduce a new media access control (MAC) spoofing attack scenario injecting artificial noise, where the prediction accuracy of Wi-Fi-based indoor localization system significantly decreases. We also propose a new deep learning-based indoor localization method using random forest(RF)-filter to provide the good prediction accuracy under the new MAC spoofing attack scenario. From the experimental results, we show that the proposed indoor localization method provides much higher prediction accuracy than the previous methods in environments with artificial noise.

Prediction of outcomes in young adults with aneurysmal subarachnoid hemorrhage.

Subarachnoid hemorrhage (SAH) is rare in young adults and little is known about aneurysms in this subgroup. The effect of clinical and prognostic factors on the outcome based on the Glasgow Outcome Scale (GOS) scores and the predictors of unfavorable outcomes were analyzed in young adults with aneurysmal SAH. A retrospective review of the clinical parameters, including age, sex, hypertension, smoking status, hyperlipidemia, location of the cerebral aneurysm, size of the aneurysm, multiplicity, perioperative complication such as hydrocephalus, vasospasm, and hematoma, and Hunt and Hess and Fisher grading on presentation, was conducted in 108 young adults (mean age 34.8 years) managed at our institute. The outcome was classified based on GOS grading into unfavorable (GOS scores 1-3) or favorable (GOS scores 4 or 5). The overall mortality rate was 3.7% (4/108 patients). Univariate regression analysis for the outcomes at discharge found that age at the time of presentation, male sex, size of aneurysm, multiple aneurysms, hyperlipidemia, and poor Hunt and Hess and Fischer grades were associated with unfavorable outcome. Multivariate regression analysis found independent effects of sex, multiple aneurysms, size of aneurysm, and Hunt and Hess grade on the outcome at discharge. Size of aneurysm, presence of multiple aneurysms, Hunt and Hess grade, and hypertension were the predictors of outcome at mean 2-year follow up based on multivariate exact regression analysis. The multimodal approach with aggressive medical management, early intervention, and surgical treatment might contribute to favorable long-term outcomes in patients with poor expected outcomes.