Reconstructing test labels from noisy loss functions
Machine learning classifiers rely on loss functions for performance evaluation, often on a private (hidden) dataset. In a recent line of research, label inference was introduced as the problem of reconstructing the ground truth labels of this private dataset from just the (possibly perturbed) cross-entropy loss function values evaluated at chosen prediction vectors (without any other access to the hidden dataset). In this paper, we formally study the necessary and sufficient conditions under which label inference is possible from any (noisy) loss function value. Using tools from analytical number theory, we show that a broad class of commonly used loss functions, including general Bregman divergence-based losses and multiclass cross-entropy with common activation functions like sigmoid and softmax, it is possible to design label inference attacks that succeed even for arbitrary noise levels and using only a single query from the adversary. We formally study the computational complexity of label inference and show that while in general, designing adversarial prediction vectors for these attacks is co-NPhard, once we have these vectors, the attacks can also be carried out through a lightweight augmentation to any neural network model, making them look benign and hard to detect. The observations in this paper provide a deeper understanding of the vulnerabilities inherent in modern machine learning and could be used for designing future trustworthy ML.