Cleaning the Null Space: A Privacy Mechanism for Predictors
Authors: Ke Xu, Tongyi Cao, Swair Shah, Crystal Maung, Haim Schweitzer
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluated the proposed algorithms on benchmark datasets from Mulan repository (Tsoumakas et al. 2011) shown in Table 1. Experimental results are averaged over 10 runs. |
| Researcher Affiliation | Academia | Ke Xu, Tongyi Cao, Swair Shah, Crystal Maung, Haim Schweitzer {ke.xu5,swair,hschweitzer}@utdallas.edu, tcao@umass.edu, Crystal.Maung@gmail.com Department of Computer Science, Univ. of Texas at Dallas. CICS, UMass Amherst. |
| Pseudocode | Yes | Figure 1: Solving the Fractional Knapsack; Figure 2: Algorithm 1 for cleaning a feature vector x.; Figure 3: Algorithm 2 for cleaning a feature vector x.; Figure 5: A proposed attack on the cleaning algorithms. |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release) for the source code of the methodology described. |
| Open Datasets | Yes | We evaluated the proposed algorithms on benchmark datasets from Mulan repository (Tsoumakas et al. 2011) shown in Table 1. |
| Dataset Splits | No | The paper states: "In each run 90% of the dataset is chosen randomly to compute the model of the ally. The rest is used as testing data...". This describes a training and testing split, but does not explicitly mention a separate validation set or its split percentage. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. It only implies computation on general resources by discussing experimental runs. |
| Software Dependencies | No | The paper mentions using "Mulan repository" for datasets, which implies software, but does not specify any software names with version numbers for reproducibility. |
| Experiment Setup | No | The paper describes the overall algorithms and experimental setup (e.g., data splitting), but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations for the models used. |