Ge Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ge Ren has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Gaolei Li
Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Shenghong Li
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Bo Zhang
School of Cyber Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Hao Peng
School of Computer Science and Technology, Zhejiang Normal University, Jinhua, Zhejiang, China
1 shared publication - Jun Wu
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Liangjie Liu
Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Shanghai Jiao Tong University, Shanghai 200030, China
1 shared publication
Latest Publications
- 8 June 2025
- Published by Springer Nature
- p. 253-268
SegDaemon: Actively Protecting Semantic Segmentation Models Against Intellectual Property Infringement
- 8 June 2025
- Published by Springer Nature
- p. 253-268
SegDaemon: Actively Protecting Semantic Segmentation Models Against Intellectual Property Infringement
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (2) , 600-617
Protecting Intellectual Property With Reliable Availability of Learning Models in AI-Based Cybersecurity Services
Artificial intelligence (AI)-based cybersecurity services offer significant promise in many scenarios, including malware detection, content supervision, and so on. Meanwhile, many commercial and government applications have raised the need for intellectual property protection of using deep neural network (DNN). Existing studies (e.g., watermarking techniques) on intellectual property protection only aim at inserting secret information into DNNs, allowing producers to detect whether the given DNN infringes on their own copyrights. However, since the availability protection of learning models is rarely considered, the piracy model can still work with high accuracy. In this paper, a novel model locking (M-LOCK) scheme for the DNN is proposed to enhance its availability protection, where the DNN produces poor accuracy if a specific token is absent, while it maps only the tokenized inputs into correct predictions. The proposed scheme performs the verification process during the DNN inference operation, actively protecting models' intellectual property copyright at each query. Specifically, to train the token-sensitive decision-making boundaries of DNNs, a data poisoning-based model manipulation (DPMM) method is also proposed, which minimizes the correlation between the dummy outputs and correct predictions. Extensive experiments demonstrate the proposed scheme could achieve high reliability and effectiveness across various benchmark datasets as well as typical model protection methods.
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (2) , 600-617
Protecting Intellectual Property With Reliable Availability of Learning Models in AI-Based Cybersecurity Services
Artificial intelligence (AI)-based cybersecurity services offer significant promise in many scenarios, including malware detection, content supervision, and so on. Meanwhile, many commercial and government applications have raised the need for intellectual property protection of using deep neural network (DNN). Existing studies (e.g., watermarking techniques) on intellectual property protection only aim at inserting secret information into DNNs, allowing producers to detect whether the given DNN infringes on their own copyrights. However, since the availability protection of learning models is rarely considered, the piracy model can still work with high accuracy. In this paper, a novel model locking (M-LOCK) scheme for the DNN is proposed to enhance its availability protection, where the DNN produces poor accuracy if a specific token is absent, while it maps only the tokenized inputs into correct predictions. The proposed scheme performs the verification process during the DNN inference operation, actively protecting models' intellectual property copyright at each query. Specifically, to train the token-sensitive decision-making boundaries of DNNs, a data poisoning-based model manipulation (DPMM) method is also proposed, which minimizes the correlation between the dummy outputs and correct predictions. Extensive experiments demonstrate the proposed scheme could achieve high reliability and effectiveness across various benchmark datasets as well as typical model protection methods.