Yeming Yang

Topology-Weighted Effective Rank: A Zero-Cost Proxy for Training Dynamics Stability in Neural Architecture Search

Haojie Zhang, Yeming Yang, Songbai Liu, Lijia Ma et autres

cn, hk (code pays fourni par la source)

Privacy-Preserving Facial Authentication with Hybrid Fuzzy Commitment and Cancelable Transformation

W. Guo, Shuaichao Song, Yeming Yang, Yuming Liao et autres

The widespread deployment of deep learning-based face recognition systems raises significant concerns regarding the security and privacy of their stored facial templates. Unlike passwords, a compromised template is irrevocable and can be inverted to reconstruct the user’s original biometric data, leading to …

cn (code pays fourni par la source)

Multiobjective Multitasking Optimization With Decomposition-Based Adaptive Knowledge Transfer

Jia Wang, Yongfeng Li, Yeming Yang, Lingjie Li et autres

Multiobjective multitasking optimization (MTO) is an emerging research direction in the evolutionary computation community, which tries to solve multiple optimization problems concurrently by utilizing shared search knowledge among related tasks. However, most existing algorithms of MTO achieve the knowledge transfer without quantifying …

cn (code pays fourni par la source)

SCGAN: Sampling and Clustering-Based Neural Architecture Search for GANs

Qingling Zhu, Yeming Yang, Songbai Liu, Qiuzhen Lin et autres

The evolutionary neural architecture search for generative adversarial networks (GANs) has demonstrated promising performance for generating high-quality images. However, two challenges persist, including the long search times and unstable search results. To alleviate these problems, this paper proposes a sampling and clustering-based …

cn, hk (code pays fourni par la source)

Cancelable binary biometric template generation scheme based on partial walsh transformation and MinHash algorithm

Yeming Yang, Yu Miao, Yuming Liao, W. Guo et autres

cn (code pays fourni par la source)

Multi-server Password authenticated Key Exchange Protocol Based on MLWE

Yeming Yang, Shuaichao Song

Currently, PAKE (Password Authenticated Key Exchange) protocols on lattice using a single-server architecture are widely applied. However, such protocols are vulnerable to server leakage attacks, dictionary attacks, and other threats. To address these issues, researchers have proposed multi-server and two-server architecture-based PAKE …

cn (code pays fourni par la source)

Two-server Password authenticated Key Exchange Protocol Based on MLWE

Yeming Yang, Shuaichao Song

Currently, PAKE (Password Authenticated Key Exchange) protocols on lattice using a single-server architecture are widely applied. However, such protocols are vulnerable to server leakage attacks, dictionary attacks, and other threats. To address these issues, researchers have proposed multi-server and two-server architecture-based PAKE …

cn (code pays fourni par la source)

A Lightweight Cancelable Biometric Template Protection Scheme

Songhui Guo, Yeming Yang, Yu Miao, Ruiyang Ding

cn (code pays fourni par la source)

Multi-objective evolutionary neural architecture search for network intrusion detection

Qiuzhen Lin, Zhihao Liu, Yeming Yang, Ka‐Chun Wong et autres

cn, hk (code pays fourni par la source)

CAGAN: Constrained neural architecture search for GANs

Yeming Yang, Xinzhi Zhang, Qingling Zhu, Wei–Neng Chen et autres

cn, hk (code pays fourni par la source)

NAS-SW: Efficient Neural Architecture Search with Stage-Wise Search Strategy

Jikun Nie, Yeming Yang, Qingling Zhu, Qiuzhen Lin

A number of Neural Architecture Search (NAS) methods have been proposed to automate the design of Convolutional Neural Networks (CNNs). However, they typically require significant computational resources and exhibit search instability. To save computational costs, many NAS methods design only a single …

cn (code pays fourni par la source)

Deep Reinforcement Learning-Based Multi-Agent Algorithm for Vehicle Routing Problem in Complex Logistics Scenarios

Xinzhi Zhang, Yeming Yang, Junchuang Cai, Qingling Zhu et autres

The Vehicle Routing Problem with Simultaneous Pickup-Delivery and Time Windows (VRPSPDTW) is a highly challenging issue in complex logistics distribution scenarios, requiring an optimal balance between cost and efficiency. Traditional methods often rely on single heuristic or metaheuristic algorithms, which perform not …

cn (code pays fourni par la source)