Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in ACM CCS, 2021
We take the first step quantifying the privacy risks of recommender systems through the lens of membership inferencek.
Download here
Published in arXiv, 2023
We find that the distribution gap of predicted labels between the training and the testing time might be the cause of robust overfitting.
Download here
Published in IEEE/CVF WACV, 2024
We propose the first generalized membership inference attack against a variety of generative models such as generative adversarial networks, [variational] autoencoders, implicit functions, and the emerging diffusion models.
Download here