3 papers
cs.LG2026
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…
cs.LG2025
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…
cs.LG2025
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…