Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their potential vulnerability to score-based membership inference attacks (MIAs). In these attacks, adversaries can infer whether a particular data sample was used during training by analyzing the model's prediction scores. However, our investigations reveal that these score-based MIAs are ineffective when targeting fairness-enhanced models in binary classifications. The attack models trained to launch the MIAs degrade into simplistic threshold models, resulting in lower attack performance. Meanwhile, we observe that fairness methods often lead to prediction performance degradation for the majority subgroups of the training data. This raises the barrier to successful attacks and widens the prediction gaps between member and non-member data. Building upon these insights, we propose an efficient MIA method against fairness-enhanced models based on fairness discrepancy results (FD-MIA). It leverages the difference in the predictions from both the original and fairness-enhanced models and exploits the observed prediction gaps as attack clues. We also explore potential strategies for mitigating privacy leakages. Extensive experiments validate our findings and demonstrate the efficacy of the proposed method.

翻译：先前的研究针对存在特定子群体歧视行为的偏倚模型开发了公平性方法。尽管这些模型在实现公平预测方面展现出潜力，但近期研究发现它们对基于分数的成员推理攻击（MIAs）存在潜在脆弱性。在这类攻击中，攻击者可通过分析模型预测分数推断特定数据样本是否被用于训练。然而，我们的研究表明，针对二分类场景中经过公平性增强的模型，这类基于分数的MIAs效率低下。用于执行MIAs的攻击模型会退化为简单的阈值模型，导致攻击性能下降。同时，我们注意到公平性方法往往导致训练数据中多数子群体预测性能下降，这既提高了成功攻击的门槛，又拉大了成员与非成员数据之间的预测差距。基于这些发现，我们提出了一种针对公平性增强模型的高效成员推理攻击方法（FD-MIA），该方法利用原始模型与公平性增强模型预测结果的差异性，并将所观测到的预测差距作为攻击线索。我们还探讨了缓解隐私泄露的潜在策略。大量实验验证了我们的发现，并证明了所提出方法的有效性。