JT
Jinyu Tian
Macau University of Science and Technology, University of Macau, Chongqing University
Research areas: Computer Science · Computer Vision and Pattern Recognition · Adversarial Robustness in Machine Learning · Digital Media Forensic Detection · Face and Expression Recognition
0000-0002-2449-5277
Employment
- 2022 - Present
Education
-
University of Macau Doctor2017 - 2022
-
Chongqing University Master2014 - 2017
-
Chongqing University Bachelor2010 - 2014
Projects & Funding
Projects & funding information is unavailable.
Publications (64)
- Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization Save
- ETV-Attack: Efficient Text-Driven Visual-Variable Adversarial Attacks on Visual Question Answering with Pre-trained Language Models Save
- OAD-Promoter: Enhancing Zero-Shot VQA Using Large Language Models with Object Attribute Description Save
- Refined Generation-Based Framework for Consistent and Reliable Visual Question Answering Save
- Robust Graph Neural Networks via Supervised Block Diagonal Regularizer Save
- Short-term electricity load forecasting with multi-frequency reconstruction diffusion Save
- AI-Backed Network Security for Connecting Air, Space, and Ground Save
- Adversarial Examples Can Actually Help to Enhance Adversarial Transferability Save
- Anti-diffusion: Preventing abuse of modifications of diffusion-based models Save
- DFFormer: Capturing Dynamic Frequency Features to Locate Image Manipulation through Adaptive Frequency Transformer and Prototype Learning Save
- Data-free universal attack by exploiting the intrinsic vulnerability of deep models Save
- RML++: Regroup Median Loss for Combating Label Noise Save
- Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era Save
- Ribonucleic-acid protein interaction prediction based on deep learning: A comprehensive survey Save
- Security within security: Attack detection model with defenses against attacks capability for zero-trust networks Save
- Towards Robust Learning via Core Feature-aware Adversarial Training Save
- A dense video caption dataset of student classroom behaviors and a baseline model with boundary semantic awareness Save
- AI and digital twin for consumer electronics in smart cities Save
- Dat: Improving adversarial robustness via generative amplitude mix-up in frequency domain Save
- DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain Save