Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study

ArXi:2502.06567v2 Announce Type: replace-cross Quantizing machine learning models has nstrated its effectiveness in lowering memory and inference costs while maintaining performance levels comparable to those of the original models. In this work, we investigate the impact of quantization procedures on privacy in data-driven models, focusing on their vulnerability to membership inference attacks. Membership Inference Security (MIS) has recently been proposed to characterize the privacy of machine learning models against the most powerful (and possibly unknown) attacks.