Data is the key factor to drive the development of machine learning (ML) during the past decade. However, high-quality data, in particular labeled data, is often hard and expensive to collect. To leverage large-scale unlabeled data, self-supervised learning, represented by contrastive learning, is introduced. The objective of contrastive learning is to map different views derived from a training sample (e.g., through data augmentation) closer in their representation space, while different views derived from different samples more distant. In this way, a contrastive model learns to generate informative representations for data samples, which are then used to perform downstream ML tasks. Recent research has shown that machine learning models are vulnerable to various privacy attacks. However, most of the current efforts concentrate on models trained with supervised learning. Meanwhile, data samples' informative representations learned with contrastive learning may cause severe privacy risks as well. In this paper, we perform the first privacy analysis of contrastive learning through the lens of membership inference and attribute inference. Our experimental results show that contrastive models trained on image datasets are less vulnerable to membership inference attacks but more vulnerable to attribute inference attacks compared to supervised models. The former is due to the fact that contrastive models are less prone to overfitting, while the latter is caused by contrastive models' capability of representing data samples expressively. To remedy this situation, we propose the first privacy-preserving contrastive learning mechanism, Talos, relying on adversarial training. Empirical results show that Talos can successfully mitigate attribute inference risks for contrastive models while maintaining their membership privacy and model utility.
翻译:在过去十年中,数据是推动机器学习(ML)发展的关键因素。然而,高质量的数据,特别是标签数据,往往很难收集,而且费用昂贵。为了利用大规模无标签数据,引入了以对比性学习为代表的自我监督学习。对比学习的目的是绘制从培训样本(例如,通过数据增强)中得出的不同观点,而从不同样本中得出的不同观点更接近其代表空间,而从不同样本中得出的不同观点则更为遥远。这样,一个对比性直率模型学会为数据样本制作信息化的演示,然后用于下游 ML任务。最近的研究表明,机器学习模型很容易受到各种隐私攻击。然而,目前多数努力集中于经过监督学习的模型。与此同时,通过对比性学习而获得的数据样本信息可能带来严重的隐私风险。在本文中,我们通过成员比例推断和属性推断的透视镜,对对比性模型的对比性分析结果显示,我们所培训的对比性模型在进行对比性分析时,对于下游数据模型的难度较小,但对于测量性模型的精确度则更弱于成员攻击程度,同时对前一个对比性模型进行对比性对比性对比性模型。对比性模型显示,而前的对比性模型则显示,比前一个比较性攻击力性比前的对比性模型的概率性能能更弱性能显示,而后比力性比力则显示性能显示前的概率性能显示性能显示,比力性模型的比力性能显示,比力性模型,比力性能显示,比力则显示性比力性能显示性能显示,比力性能度则表明,比力性能度则显示,比力性能显示,比力性比力性比力性能力性能显示,比力性能显示,比力性比力性比力性比力性比力性比力性能,比力性模型。