A membership inference attack (MIA) poses privacy risks on the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The stateof-the-art defense against MIAs, distillation for membership privacy (DMP), requires not only private data to protect but a large amount of unlabeled public data. However, in certain privacy-sensitive domains, such as medical and financial, the availability of public data is not obvious. Moreover, a trivial method to generate the public data by using generative adversarial networks significantly decreases the model accuracy, as reported by the authors of DMP. To overcome this problem, we propose a novel defense against MIAs using knowledge distillation without requiring public data. Our experiments show that the privacy protection and accuracy of our defense are comparable with those of DMP for the benchmark tabular datasets used in MIA researches, Purchase100 and Texas100, and our defense has much better privacy-utility trade-off than those of the existing defenses without using public data for image dataset CIFAR10.

No abstract

A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs, distillation for membership privacy (DMP), requires not only private data for protection but a large amount of unlabeled public data. However, in certain privacy-sensitive domains, such as medicine and finance, the availability of public data is not guaranteed. Moreover, a trivial method for generating public data by using generative adversarial networks significantly decreases the model accuracy, as reported by the authors of DMP. To overcome this problem, we propose a novel defense against MIAs that uses knowledge distillation without requiring public data. Our experiments show that the privacy protection and accuracy of our defense are comparable to those of DMP for the benchmark tabular datasets used in MIA research, Purchase100 and Texas100, and our defense has a much better privacy-utility trade-off than those of the existing defenses that also do not use public data for the image dataset CIFAR10.

<p>In this study, an influence line of girder deflection of the bridge was calculated for the initial calibration of Bridge Weigh-in-Motion (B-WIM). The deflection responses were obtained from the proposed integration process using the baseline correction. Optical flow analysis was applied using a video camera to adapt to the variable vehicle speed and precisely measure the location of vehicles on a bridge. A foreground mask using the Gaussian mixture model and a Kalman filter was then applied to identify the vehicles. A calibration process of B-WIM was proposed using the iteration process to optimize the influence line of deflection using local buses in regular traffic. Finally, the axle weights of a weight-known test truck were analyzed by monitoring with the video camera and acceleration sensor. Compared with conventional B-WIM methods, the proposed method has demonstrated higher adaptability in variable vehicle speed.</p>