Junmo Kim

Reinforcement Learning-Based Black-Box Model Inversion Attacks

2023 · arXiv (Cornell University)

Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative Adversarial Networks (GANs) …

Disposable Transfer Learning for Selective Source Task Unlearning

2023 · arXiv (Cornell University)

Transfer learning is widely used for training deep neural networks (DNN) for building a powerful representation. Even after the pre-trained model is adapted for the target task, the representation performance of the feature extractor is …