Searched for: +
(21 - 40 of 87)

Pages

document
Koffas, S. (author), Xu, J. (author), Conti, M. (author), Picek, S. (author)
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for legitimate users and, consequently, potentially more dangerous. We conduct experiments on two versions of a speech dataset and three neural networks and explore the...
conference paper 2022
document
Xu, M. (author), Chavez Tapia, M.A. (author), Zuniga, Marco (author)
There is a growing interest in exploiting ambient light for wireless communication. This new research area has two key advantages: it utilizes a free portion of the spectrum and does not require modifications of the lighting infrastructure. Most existing designs, however, rely on a single type of optical surface at the transmitter: liquid...
conference paper 2022
document
Zhang, Xinglong (author), Peng, Yaoqian (author), Pan, W. (author), Xu, Xin (author), Xie, Haibin (author)
Distributed model predictive control (DMPC) concerns how to online control multiple robotic systems with constraints effectively. However, the nonlinearity, nonconvexity, and strong interconnections of dynamic system models and constraints can make the real-time and real-world DMPC implementations nontrivial. Reinforcement learning (RL)...
conference paper 2022
document
Xia, Fei (author), Gevers, Monique (author), Fognini, Andreas (author), Mok, Aaron T. (author), Li, Bo (author), Akabri, Najva (author), Esmaeil Zadeh, I.Z. (author), Qin-Dregely, Y. (author), Xu, Chris (author)
Using short-wave infrared wavelength advantages, we demonstrate one-photon fluorescence confocal microscopy of adult mouse brains with penetration depths up to 1.7mm. This is achieved by labeling quantum dots with 1300 nm excitation and 1700 nm emission and detecting them with a single-photon superconducting nanowire detector.
conference paper 2022
document
Xu, J. (author), Picek, S. (author)
Graph Neural Networks (GNNs) have achieved impressive results in various graph learning tasks. They have found their way into many applications, such as fraud detection, molecular property prediction, or knowledge graph reasoning. However, GNNs have been recently demonstrated to be vulnerable to backdoor attacks. In this work, we explore a...
conference paper 2022
document
Xu, J. (author), Wang, R. (author), Koffas, S. (author), Liang, K. (author), Picek, S. (author)
Graph Neural Networks (GNNs) are a class of deep learning-based methods for processing graph domain information. GNNs have recently become a widely used graph analysis method due to their superior ability to learn representations for complex graph data. Due to privacy concerns and regulation restrictions, centralized GNNs can be difficult to...
conference paper 2022
document
Conti, M. (author), Li, Jiaxin (author), Picek, S. (author), Xu, J. (author)
Graph Neural Networks (GNNs), inspired by Convolutional Neural Networks (CNNs), aggregate the message of nodes' neighbors and structure information to acquire expressive representations of nodes for node classification, graph classification, and link prediction. Previous studies have indicated that node-level GNNs are vulnerable to Membership...
conference paper 2022
document
Zheng, Yubo (author), Xu, Peng (author), Wang, Wei (author), Chen, Tianyang (author), Susilo, Willy (author), Liang, K. (author), Jin, Hai (author)
Many practical secure systems have been designed to prevent real-world attacks via maximizing the attacking cost so as to reduce attack intentions. Inspired by this philosophy, we propose a new concept named delay encryption with keyword search (DEKS) to resist the notorious keyword guessing attack (KGA), in the context of secure cloud-based...
conference paper 2022
document
Xu, Jingyi (author), Li, Z. (author), Gao, Li (author), Ma, Junyi (author), Liu, Qi (author), Zhao, Yanan (author)
The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which is a time-consuming and laborious task. A more efficient way of choosing EMS is to combine deep reinforcement learning (DRL)...
conference paper 2022
document
Xu, Zhenhai (author), Gao, Jianming (author), Chen, Fei (author)
Cement-based materials in sulfate rich areas will suffer from serious corrosion after semi-immersion. To study the degradation of cement mortars with different water cement ratio (w/c) partially exposed to sulfate solution, the mass change were employed to reveal damage progress. Moreover, porosity, erosion products and SO2 4 - content were...
conference paper 2021
document
Li, Shuguang (author), Jia, Jinsheng (author), Xu, Yaoqun (author), Zhai, Xiangjun (author), Li, Xiulin (author), Chen, Gaixin (author)
In order to evaluate the aging status of the dam concrete for a 25-years-old concrete dam, the internal concrete and surface layer of the dam were tested by elastic wave computerized tomography (CT) and spectral analysis of surface wave (SASW). Also mechanical strength and elastic wave velocity were tested for the concrete cores from the dam....
conference paper 2021
document
Xu, Zhiyuan (author), Zuo, Yibing (author), Ye, Guang (author)
In this work, a numerical model is proposed to study chloride transport in alkali-activated materials. This model is based on multiple-relaxation-time lattice Boltzmann method, where particle distribution function is introduced to simulate the chloride binding and diffusion. This model takes into account diffusion, homogenous reaction between...
conference paper 2021
document
Pang, Min (author), Sun, Zhenping (author), Ji, Yanliang (author), Yang, Jingbin (author), Wang, Peiming (author), Xu, Yaling (author), Li, Huanhuan (author), Liu, Jiaying (author), Li, Fei (author)
Characteristics of fly ash(FA) blended mortars (50%, 70% and 90%) at different curing ages (28 days and 180 days) under ammonium chloride solution(ACS) leaching were investigated. Mass loss under leaching, initial CaO content, Ca(OH)2 content(CH), content of chemical bonded water, and hydration degree of blended pastes were tested by XRF and DSC...
conference paper 2021
document
Xu, Z. (author), Zuo, Y. (author), Ye, G. (author)
In this work, a numerical model is proposed to study chloride transport in alkali-activated materials. This model is based on multiple-relaxation-time lattice Boltzmann method, where particle distribution function is introduced to simulate the chloride binding and diffusion. This model takes into account diffusion, homogenous reaction between...
conference paper 2021
document
Wu, Y. (author), Soeiro, Thiago B. (author), Shekhar, A. (author), Xu, J. (author), Bauer, P. (author)
LCL filter is widely adopted for strict standard compliance of grid-tied voltage source converters (VSCs). The third order low-pass filtering provides great attenuation for the high frequency harmonics generated by the power electronics guaranteeing low output currents noise injection into the grid. A major concern of the implementation of the...
conference paper 2021
document
Ping, Y. (author), Yao, X. (author), Xu, J. (author), Li, Juntian (author), Song, Y. (author), Vink, P. (author)
The angle of attack (AOA) of an airplane changes the direction of the gravitational force on passengers and thereby might influence passengers’ flying experience. However, the contribution of the AOA regarding comfort/discomfort is not fully explored. In this paper, we aim to fill this knowledge gap by identifying the relationships between the...
conference paper 2021
document
Xu, Luyan (author), Zhuang, Mengdie (author), Gadiraju, Ujwal (author)
Understanding the influence of users' opinions on their search behavior together with their inherent biases in web search has garnered widespread interest in recent times. This is largely due to the implications of promoting critical thinking, explaining phenomena such as political polarization, or the manifestation of echo chambers. It is...
conference paper 2021
document
Valinejad, Jaber (author), Mili, Lamine (author), van der Wal, C.N. (author), Von Spakovsky, Michael (author), Xu, Yijun (author)
Power systems serve social communities that consist of residential, commercial, and industrial customers. As a result, the disaster resilience of a power system should account for social community resilience. The social behavior and psychological features of all stakeholders involved in a disaster influence the level of power system preparedness...
conference paper 2021
document
Xu, J. (author), Xue, Minhui (author), Picek, S. (author)
Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous works on backdoor attacks on neural networks, but only a few works consider graph neural...
conference paper 2021
document
Xu, Junzhong (author), Gao, Fei (author), Soeiro, Thiago B. (author), Chen, Linglin (author), Tarisciotti, Luca (author), Tang, Houjun (author), Bauer, P. (author)
The implementation of traditional finite-control-set model predictive control (FCS-MPC) with variable switching frequency in voltage source rectifiers (VSRs) can make the system suffer from poor current harmonics performance. In fact, the resulting wide-spread voltage harmonic generated at the AC terminals makes the design of the typical multi...
conference paper 2020
Searched for: +
(21 - 40 of 87)

Pages