DDoS Event Forecasting using Twitter Data

Authors: Zhongqing Wang, Yue Zhang

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluation shows that social text streams are indeed informative for DDo S forecasting, and our proposed hierarchical model is more effective compared to strong baseline text stream models and discrete bag-of-words models.
Researcher Affiliation Academia Zhongqing Wang , and Yue Zhang Soochow University, Suzhou, China Singapore University of Technology and Design, Singapore
Pseudocode No No explicit pseudocode or algorithm blocks are provided. Model descriptions are given in text and mathematical formulas.
Open Source Code Yes Our code and dataset are both available at https://github.com/wangzq870305/ddos forecast.
Open Datasets Yes For building our benchmark dataset, we collect these three types of information from ddosattacks.net... Our code and dataset are both available at https://github.com/wangzq870305/ddos forecast.
Dataset Splits Yes We use 80 random targets for training, 60 for development, and the remaining 30 for testing.
Hardware Specification No The paper does not explicitly describe the specific hardware used for its experiments (e.g., CPU, GPU models, memory).
Software Dependencies No The paper mentions tools like "SV M light" and "Skip-gram algorithm" but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes For LSTM stream models, we empirically set the size of hidden layers to 32. For CNNs, the dimension of the input layer is set to 128, and the output dimension of convolution layers is 32. In order to avoid over-fitting, dropout [Hinton et al., 2012] is applied to word embeddings with a ratio of 0.2. We apply online training, optimizing parameters by using Adagrad [Duchi et al., 2011].