2 papers
cs.CR2025
From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
Ziang Li, Hongguang Zhang, Juan Wang +6
Model Inversion Attacks (MIAs) aim to reconstruct private training data from models, leading to privacy leakage, particularly in facial recognition systems. Although many studies h…
cs.CR2024
Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks
Yu He, Boheng Li, Yao Wang +4
The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has garnered considerable attention in recent years. These attacks determine whether a data samp…