activity
20062023
most citedDeep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

539 citations · 1.1k across the 28 of their papers we have counts for

collaborators

28 papers

cs.CR2023★ 2 cited

Privacy Attacks and Defenses for Digital Twin Migrations in Vehicular Metaverses

Xiaofeng Luo, Jinbo Wen, Jiawen Kang +5

The gradual fusion of intelligent transportation systems with metaverse technologies is giving rise to vehicular metaverses, which blend virtual spaces with physical space. As indi…

cs.LG2023

Combinatorial Auctions and Graph Neural Networks for Local Energy Flexibility Markets

Awadelrahman M. A. Ahmed, Frank Eliassen, Yan Zhang

This paper proposes a new combinatorial auction framework for local energy flexibility markets, which addresses the issue of prosumers' inability to bundle multiple flexibility tim…

cs.CV2023★ 2 cited

PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow

Lin Yuan, Kai Liang, Xiao Pu +5

This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single…

cs.CV2023★ 3 cited

Fast and Stable Diffusion Inverse Solver with History Gradient Update

Linchao He, Hongyu Yan, Mengting Luo +8

Diffusion models have recently been recognised as efficient inverse problem solvers due to their ability to produce high-quality reconstruction results without relying on pairwise…

cs.LG2023★ 1 cited

Balancing Explainability-Accuracy of Complex Models

Poushali Sengupta, Yan Zhang, Sabita Maharjan +1

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches…

cs.CL2023★ 1 cited

Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation

Danqing Luo, Chen Zhang, Jiahui Xu +4

Training or finetuning large-scale language models (LLMs) such as GPT-3 requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptat…