CD
Changyu Dong
Guangzhou University, Newcastle University, Imperial College London
Research areas: Computer Science · Computer Networks and Communications · Cryptography and Data Security · Cloud Data Security Solutions · Privacy-Preserving Technologies in Data
0000-0002-8625-0275
Employment
-
Guangzhou University Professor2022 - Present
-
Newcastle University Senior Lecturer in Security2016 - Present
Education
- 2005 - 2009
Projects & Funding
-
Practical Data-intensive Secure Computation: a Data Structural Approach Engineering and Physical Sciences Research Council2016 - 2016
Publications (29)
- Fortified Concept Forgetting for text-to-image generative models by machine unlearning on CLIP Save
- Graph-Based Contract Sensing Framework for Smart Contract Vulnerability Detection Save
- Online Self-Distillation and Self-Modeling for 3D Brain Tumor Segmentation Save
- Hierarchical Network With Local-Global Awareness for Ethereum Account De-anonymization Save
- SAMamba: Structure-Aware Mamba for Ethereum Fraud Detection Save
- Side-Channel Attacks and New Principles in the Shuffle Model of Differential Privacy Save
- Toward Cross-Environment Continuous Gesture User Authentication With Commercial Wi-Fi Save
- A Game Theory Reward Model for Federated Learning with Probabilistic Verification Save
- DISCO: Dynamic Searchable Encryption with Constant State Save
- ZeroMT: Towards Multi-Transfer transactions with privacy for account-based blockchain Save
- Defenses to Membership Inference Attacks: A Survey Save
- Sphinx-in-the-Head: Group Signatures from Symmetric Primitives Save
- A New Hash-Based Enhanced Privacy ID Signature Scheme Save
- A Survey of Privacy Preserving Subgraph Matching Methods Save
- Distributed Differential Privacy via Shuffling Versus Aggregation: A Curious Study Save
- Boost Off/On-Manifold Adversarial Robustness for Deep Learning with Latent Representation Mixup Save
- Defending Against Membership Inference Attacks With High Utility by GAN Save
- Hash-Based Direct Anonymous Attestation Save
- Differentially Private Byzantine-Robust Federated Learning Save
- EncodeORE: Reducing Leakage and Preserving Practicality in Order-Revealing Encryption Save