Label-only Model Inversion Attack: The Attack that Requires the Least Information
This addresses a security vulnerability for model owners who rely on label-only outputs as a defense, revealing a more accessible attack vector.
The authors tackled the problem of model inversion attacks with minimal information by developing a method that reconstructs training data using only predicted labels, achieving highly recognizable reconstructions with far less information than existing methods.
In a model inversion attack, an adversary attempts to reconstruct the data records, used to train a target model, using only the model's output. In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i.e., black-box attacks, or the parameters of a target model, i.e., white-box attacks. However, in the real world, model owners usually only give out the predicted labels; the confidence score vectors and model parameters are hidden as a defense mechanism to prevent such attacks. Unfortunately, we have found a model inversion method that can reconstruct the input data records based only on the output labels. We believe this is the attack that requires the least information to succeed and, therefore, has the best applicability. The key idea is to exploit the error rate of the target model to compute the median distance from a set of data records to the decision boundary of the target model. The distance, then, is used to generate confidence score vectors which are adopted to train an attack model to reconstruct the data records. The experimental results show that highly recognizable data records can be reconstructed with far less information than existing methods.