Dataset of Membership Inference Attack Defense Strategies
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".