Ngoc-Bao Nguyen

4 papers · 2023–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner (2)

Venues

CVPR (3) ECCV (1)

Top co-authors

Ngai-Man Cheung (4) Sy-Tuyen Ho (3) Koh Jun Hao (2) Keshigeyan Chandrasegaran (2) Milad Abdollahzadeh (1) Jun Hao Koh (1)

Research topics

Deep Learning (3) Artificial Intelligence (2) Machine Learning (2) Security & Privacy (2) Application Areas (2) Privacy (2) Architectures (1) Core AI (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Techniques (1)

Keywords

model inversion (2) model inversion attack (2) face recognition (1) deep learning (1) fisher information (1) generative model (1) deep neural network (1) adversarial defense (1) vision-language model (1) skip connection (1) reconstruction attack (1) gradient weighting (1) training data leakage (1) privacy (1) mi-resilient architectures (1) privacy attack (1) repvgg (1) transfer learning (1)

Papers

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks CVPR 2026 Model Inversion Robustness: Can Transfer Learning Help? CVPR 2024 On the Vulnerability of Skip Connections to Model Inversion Attacks ECCV 2024 Re-Thinking Model Inversion Attacks Against Deep Neural Networks CVPR 2023