Yaohua Luo

Yaohua Luo

Auto-generated profile, based on publicly available information

Yaohua Luo

School of Computer and Cybersecurity, Chengdu University of Technology, Chengdu, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2020 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
DCDajiang Chen
Dajiang Chen
ZZZihao Zhao
Zihao Zhao
XQXue Qin
Xue Qin
YLYaohua Luo
Yaohua Luo
MCMingsheng Cao
Mingsheng Cao
Anfeng LiuAnfeng Liu
Anfeng Liu
As an emerging technology, industrial Internet of Things (IIoT) connects massive sensors and actuators to empower industrial sectors being smart, autonomous, efficient, and safety. However, due the large number of build-in sensors of IIoT smart devices, the IIoT systems are vulnerable to side-channel attack. In this article, a novel side-channel-based passwords cracking system, namely MAGLeak, is proposed to recognize the victim's passwords by leveraging accelerometer, gyroscope, and magnetometer of IIoT touch-screen smart device. Specifically, an event-driven data collection method is proposed to ensure that the user's keystroke behavior can be reflected accurately by the obtained measurements of three sensors. Moreover, random forest algorithm is leveraged for the recognition module, followed by a data preprocessing process. Extensive experimental results demonstrate that MAGLeak achieves a high recognition accuracy under small training dataset, e.g., achieving recognition accuracy 98% of each single key for 2000 training samples.

19 August 2021 in Geofluids
Verified
Journal Article
Open access
PDF file
ZTZhongping Tao
Zhongping Tao
BLBingli Liu
Bingli Liu
KGKe Guo
Ke Guo
NGNa Guo
Na Guo
CLCheng Li
Cheng Li
YLYaohua Luo
Yaohua Luo
The identification of primary geochemical haloes can be used to predict mineral resources in deep-seated orebodies through the delineation of element distributions. The Jiama deposits a typical skarn–porphyry Cu–polymetallic deposit in the Gangdese metallogenic belt of Tibet. The Cu–polymetallic skarn, Cu–Mo hornfels, and Mo ± Cu porphyry mineralization there exhibit superimposed geochemical haloes at depth. Three-dimensional (3D) primary geochemical halo modeling was undertaken for the deposit with the aim of providing geochemical data to describe element distributions in 3D space. An overall geochemical zonation of Zn(Pb) → Au → Cu(Ag) → Mo gained from geochemical cross-sections, together with dip-direction skarn zonation Pb–Zn(Cu) → Cu(Au–Ag–Mo) → Mo(Cu) → Cu–Mo(Au–Ag) and vertical zonation Cu–(Pb–Zn) → Mo–(Cu) → Mo–Cu–(Ag–Au–Pb–Zn) → Mo in the #24 exploration profile, indicates potential mineralization at depth. Integrated geochemical anomalies were extracted by kernel principal component analysis, which has the advantage of accommodating nonlinear data. A maximum-entropy model was constructed for deep mineral resources of uncertainty prediction. Three potential deep mineral targets are proposed on the basis of the obtained geochemical information and background.

16 March 2020 in IEEE Access
Verified
Journal Article
Open access
CLChunwei Lou
Chunwei Lou
MCMingsheng Cao
Mingsheng Cao
YLYaohua Luo
Yaohua Luo
HXHua Xu
Hua Xu
YGYuan Gao
Yuan Gao
DWDong Wang
Dong Wang
Key-aggregate keyword retrieval primitive enables a cloud server on behalf of delegated users to securely perform a keyword search over the data encrypted with various public keys. However, existing key-aggregate searchable encryption schemes are insecure against keyword guessing attacks, which result in the privacy leakage of keyword ciphertext and trapdoor. In this paper, we for the first time formulate a secure and efficient key-aggregate searchable encryption for cloud-assisted IoT applications, which not only enables a data owner to securely share the selected documents to multiple users, but also supports data users in delegating the capability of keyword search to a cloud server for searching the desired documents without leaking any privacy of keyword ciphertext and trapdoor. Then, the security of the proposed scheme is formally defined and proven to be secure against the indistinguishable selective-file chosen keyword attacks. The flexibility and practicability of the formulated scheme is also demonstrated by theoretical evaluations and experimental simulations.

18 December 2025 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
YLYaohua Luo
Yaohua Luo
LYLei Yuan
Lei Yuan
JZJianchao Zheng
Jianchao Zheng
YWYe Wang
Ye Wang
YGYuan Gao
Yuan Gao
DCDajiang Chen
Dajiang Chen
Federated learning (FL) has emerged as a natural enabler for distributed intelligence in next-generation wireless networks (e.g., 6G), particularly for realizing intelligent radio access and autonomous spectrum management. However, the integration of FL introduces critical security challenges, most no tably backdoor attacks, where adversaries compromise the global model by injecting malicious updates while maintaining benign performance. In this paper, we propose DPCTS (Decentralized Trust Propagation with Cross-Client Trust Synthesis), a novel anti-backdoor FL framework that integrates multi-dimensional trust evaluation with graph-based trust propagation via a dy namically weighted restart mechanism. Unlike existing methods that depend on on global anomaly detection, DPCTS employs a fully decentralized trust modeling paradigm. specifically, each client's trustworthiness is dynamically assessed through three complementary dimensions: behavioral consistency across local training iterations, trajectory divergence from the aggregated global model, and statistical alignment with the evolving global data distribution. Crucially, trust scores are propagated itera tively across the edges of a constructed client interaction graph, enabling each participant to accumulate indirect trust evidence from multi-hop neighbors while mitigating localized biases. The theoretical analysis proves that the trust propagation process converges to a unique fixed point and that the trust gap between benign and adversarial clients monotonically increases and sta bilizes at a positive margin, ensuring both algorithmic stability and effective trust separation. We evaluate the proposed method against state-of-the-art defenses on multiple benchmark datasets, demonstrating its superior resistance to backdoor attacks under extreme conditions while maintaining comparable model utility.

27 October 2026 in Ecological Informatics
Verified
Journal Article
Open access
ZZZhaoyi Zhang
Zhaoyi Zhang
HZHui Zhao
Hui Zhao
HJHuaan Jin
Huaan Jin
JYJing Yang
Jing Yang
QYQuanzhi Yuan
Quanzhi Yuan
YLYaohua Luo
Yaohua Luo