← Search

Koh Jun Hao

2 accepted papers

2026

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks

CVPR 2026

Model inversion (MI) attacks pose significant privacy risks by reconstructing private training data from trained neural networks. While prior studies have primarily examined unimodal deep networks, the vulnerability of vision-language models (VLMs) remains largely unexplored. In this work, we presen

Cited by 0SourcecodeScholar
2024

Model Inversion Robustness: Can Transfer Learning Help?

CVPR 2024poster

Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance posing serious threats to privacy. Meanwhile all existing MI defense methods rely on regularization that is in direc…