Adversarial Examples for Graph Data: Deep Insights into Attack and Defense

Authors: Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on a number of datasets show the effectiveness of the proposed techniques.
Researcher Affiliation Academia 1University of New South Wales, Australia 2Data61, CSIRO 3National University of Defense Technology, China
Pseudocode Yes Algorithm 1 shows the pseudo-code for untargeted IGJSMA attack.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets Yes We use the widely used CORA-ML [Mc Callum et al., 2000], CITESEER [Bojchevski and G unnemann, 2018] and Polblogs [Adamic and Glance, 2005] datasets.
Dataset Splits Yes We split each graph into a labeled (20%) set and an unlabeled set of nodes (80%). Among the labeled nodes, half of them are used for training while the rest are used for validation.
Hardware Specification No The paper does not specify any particular hardware (e.g., GPU, CPU model) used for running the experiments. It only mentions 'our non-optimized Python implementation'.
Software Dependencies No The paper mentions 'Python implementation' but does not provide specific software dependencies with version numbers (e.g., PyTorch 1.x, TensorFlow 2.x).
Experiment Setup No The paper mentions training a 'two-layer GCN' but does not provide specific hyperparameters such as learning rate, batch size, number of epochs, or optimizer details required for reproduction.