A
Anmin Fu
Researcher at Nanjing University of Science and Technology
Publications - 103
Citations - 1547
Anmin Fu is an academic researcher from Nanjing University of Science and Technology. The author has contributed to research in topics: Computer science & Cloud computing. The author has an hindex of 16, co-authored 79 publications receiving 858 citations. Previous affiliations of Anmin Fu include Nanjing University of Posts and Telecommunications & Xidian University.
Papers
More filters
Posted Content
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things.
Huming Qiu,Hua Ma,Zhi Zhang,Yifeng Zheng,Anmin Fu,Pan Zhou,Yansong Gao,Derek Abbott,Said F. Al-Sarawi +8 more
TL;DR: In this article, a reconfigurable deep binary neural network (RBNN) is proposed to further amplify the memory efficiency for resource-constrained IoT devices, which can be reconfigured on demand to achieve any one of M (M>1) distinct tasks with the same parameter set, thus only a single task determines the memory requirements.
Journal ArticleDOI
Vertical Federated Learning: Taxonomies, Threats, and Prospects
Qun Li,Chandra Thapa,Lawrence Hui Boon. Ong,Yefeng Zheng,Hua Ma,Seyit Camtepe,Anmin Fu,Yan Gao +7 more
TL;DR: Federated learning (FL) is the most popular distributed machine learning technique as mentioned in this paper , which allows machine-learning models to be trained without acquiring raw data to a single point for processing.
Towards Explainable Meta-Learning for DDoS Detection
TL;DR: A rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on artiﰁcial immune system is proposed, and a map, combine and merge (M&M) method is proposed to discretize continuous features into boolean expression and simplify into prime implicants.
Journal ArticleDOI
Systematically Evaluation of Challenge Obfuscated APUFs
TL;DR: It is shown that all five CO-APUFs with relatively large scale can be successfully modeled—attacking accuracy higher or close to its reliability and the hyper-parameter tuning of DL technique is crucial for implementing efficient attacks.
Journal ArticleDOI
CCA-Secure and Revocable Certificateless Encryption with Ciphertext Evolution
TL;DR: This research presents a probabilistic architecture suitable for identity-based and certificateless cryptosystems, and investigates the combination of these systems with each other to derive a single public key.