4 papers · 1 filter
BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning
Yongchao Huang
Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effe…
Training data membership inference via Gaussian process meta-modeling: a post-hoc analysis approach
Yongchao Huang, Pengfei Zhang, Shahzad Mumtaz
Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or he…
Bayesian Inference of Training Dataset Membership
Yongchao Huang
Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference…
Classification via score-based generative modelling
Yongchao Huang
In this work, we investigated the application of score-based gradient learning in discriminative and generative classification settings. Score function can be used to characterize…