This work investigates the vulnerability of Gaussian Mixture Model (GMM) i-vector based speaker verification (SV) systems to adversarial attacks, and the transferability of adversarial samples crafted from GMM i-vector based systems to x-vector based systems. In detail, we formulate the GMM i-vector based system as a scoring function, and leverage the fast gradient sign method (FGSM) to generate adversarial samples through this function. These adversarial samples are used to attack both GMM i-vector and x-vector based systems. We measure the vulnerability of the systems by the degradation of equal error rate and false acceptance rate. Experimental results show that GMM i-vector based systems are seriously vulnerable to adversarial attacks, and the generated adversarial samples are proved to be transferable and pose threats to neural network speaker embedding based systems (e.g. x-vector systems).

No abstract

No abstract

Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the "black box" of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

The growth of the Tibetan Plateau is related to the Cenozoic India-Eurasia plate collision; however, its growth and evolution to its present margins remain matters of debate. The Qilian Shan, which is located along the northeastern margin of the Tibetan Plateau, plays a central role in understanding the outward growth of the plateau. In this paper, we present new low-temperature thermochronologic data from the hanging wall of the Huangcheng-Shuangta fault (HSF) and the Lenglongling west region in the eastern part of the Qilian Shan. Cooling ages and thermal history modeling show increased exhumation rates at~15 Ma along the HSF and~5 Ma in the Lenglongling west region. We suggest that the middle Miocene beginning of rapid exhumation reflects the expansion of the larger Qilian Shan driven by thrust fault systems. The fast Pliocene exhumation may have been related to left-lateral motion on the Haiyuan fault during the late stage of orogenic development. Post-Miocene episodes of rapid exhumation in the eastern Qilian Shan are similar to those in other regions on the northeastern margin of the Tibetan Plateau, suggesting that middle to late Miocene initiation or acceleration of crustal shortening occurred along this margin.