Dataset of Membership Inference Attack Defense Strategies

The random number generation algorithm used within the consensus mechanism of blockchain systems may be plagued by member inference attacks, resulting in the inference of the algorithm's features or patterns of generated random numbers. Based on this issue, the research group proposed a resistance scheme based on knowledge distillation to ensure the security of the random number generation algorithm. The research group used a member inference attack defense strategy dataset to evaluate the performance of our proposed defense scheme, which includes 5 batch training datasets and 1 test dataset. By analyzing the performance changes of machine learning models after being subjected to member inference attacks on this dataset, evaluate the performance of member inference attack defense strategies. Collection plan: The folder name of the test dataset is "Member Reasoning Attack Resistance Strategy Dataset/cifar-10 patches py". CIFAR-10 is a small dataset used to identify ubiquitous objects, which can be accessed through the following link http://www.cs.toronto.edu/ ~Kriz/cifar. HTML download. Contains 10 categories of RGB color images. Each image has a size of 32 × 32. Each category has 6000 images, and there are a total of 50000 training images and 10000 test images in the dataset. Time and location: This dataset is test data collected by the research unit "Peking University" during 2021. Equipment situation: Data collection is processed in the following environment: hardware environment: supports general computing platforms such as Intel and ARM; System environment: Windows 11 and Ubuntu 20.04.