Fair Finetuning Mitigates Distribution Inference Attacks 事件

Fair Finetuning Mitigates Distribution Inference Attacks arXiv:2606.01719v1 Announce Type: cross Abstract: Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA). An adversary with black-box access can infer sensitive demographic properties, such as subgroup proportions, without observing any training data directly. While defenses such as differential privac