Longlong Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Longlong Hu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Li-Hua Gong
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science 2 , 201620 Shanghai
1 shared publication Linji Zhang
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication- Liquan Chen
Southeast University
1 shared publication - Mingfu Xue
School of Communication and Electronic Engineering, East China Normal University, Shanghai, China
1 shared publication - Yang Shi
School of Computer Science and Technology, Tongji University, Shanghai, China
1 shared publication - Zhe Guo1 shared publication
Latest Publications
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
GNNLicense: An Active Intellectual Property Protection Technique for Graph Neural Networks based on Autoencoder
Graph Neural Networks (GNNs) are widely utilized in areas such as social network analysis, recommendation systems, and fraud detection. Protecting the intellectual property (IP) of GNN models is crucial to avoid potential economic losses. However, existing researches on GNN IP protection rely on watermarking techniques for passive copyright verification. In this paper, we propose GNNLicense, the first active GNN IP protection and user’s identity management method against GNN piracy. The proposed method employs encoder-decoder models to encode and reconstruct graph features. Since the graph encoded by the encoder can only be decoded by the corresponding decoder, this design achieves active IP protection. In addition, the proposed method leverages fingerprint to manage and distinguish between different authorized users’ identities. The encoder is held by the user, while the decoder is retained by the service provider. The user encodes the input graph data through the encoder, and then submits it to the server for normal predictions. This mechanism makes unauthorized users can only obtain very poor model performance while ensures the normal use of authorized users. Experimental results on five graph datasets and five popular GNN models across node classification and graph classification tasks demonstrate the method’s effectiveness. Moreover, the method maintains its robustness when subjected to fine-tuning and adaptive attacks.
- 5 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
GNNLicense: An Active Intellectual Property Protection Technique for Graph Neural Networks based on Autoencoder
Graph Neural Networks (GNNs) are widely utilized in areas such as social network analysis, recommendation systems, and fraud detection. Protecting the intellectual property (IP) of GNN models is crucial to avoid potential economic losses. However, existing researches on GNN IP protection rely on watermarking techniques for passive copyright verification. In this paper, we propose GNNLicense, the first active GNN IP protection and user’s identity management method against GNN piracy. The proposed method employs encoder-decoder models to encode and reconstruct graph features. Since the graph encoded by the encoder can only be decoded by the corresponding decoder, this design achieves active IP protection. In addition, the proposed method leverages fingerprint to manage and distinguish between different authorized users’ identities. The encoder is held by the user, while the decoder is retained by the service provider. The user encodes the input graph data through the encoder, and then submits it to the server for normal predictions. This mechanism makes unauthorized users can only obtain very poor model performance while ensures the normal use of authorized users. Experimental results on five graph datasets and five popular GNN models across node classification and graph classification tasks demonstrate the method’s effectiveness. Moreover, the method maintains its robustness when subjected to fine-tuning and adaptive attacks.
- Top Cited Papers
- 20 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
Color image encryption and authentication algorithm integrating computational ghost imaging with quaternion multi-parameter discrete fractional angular transform
- 20 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
Top Cited PapersColor image encryption and authentication algorithm integrating computational ghost imaging with quaternion multi-parameter discrete fractional angular transform