Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Machine learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent to enlarge the loss variance of training data, alleviating the privacy risk. However, optimizing toward a reverse direction may cause the model parameters to oscillate near local minima, leading to instability and suboptimal performance. In this work, we propose a novel method -- Convex-Concave Loss, which enables a high variance of training loss …

aim attacks cs.cr cs.lg data loss machine machine learning machine learning models may privacy privacy risk reverse risk sample training training data work