Adversarial Socialbots Modeling Based on Structural Information Principles

Authors: Xianghua Zeng, Hao Peng, Angsheng Li

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive and comparative experiments on both homogeneous and heterogeneous social networks demonstrate that, compared with state-of-the-art baselines, the proposed SIASM framework yields substantial performance improvements in terms of network influence (up to 16.32%) and sustainable stealthiness (up to 16.29%) when evaluated against a robust detector with 90% accuracy.
Researcher Affiliation Academia 1 State Key Laboratory of Software Development Environment, Beihang University, Beijing, China 2 Zhongguancun Laboratory, Beijing, China {zengxianghua, penghao, angsheng}@buaa.edu.cn, liangsheng@gmail.zgclab.edu.cn
Pseudocode Yes Algorithm 1: The Optimization Algorithm
Open Source Code Yes Furthermore, all source codes and experimental results are available at an anonymous link1. 1https://github.com/SELGroup/SIASM
Open Datasets Yes For heterogeneous network analysis, we use the latest Higgs Twitter Dataset (De Domenico et al. 2013), which includes directed multi-relational interactions. Like other works (Le, Tran-Thanh, and Lee 2022), we select 10% of the real-life networks to construct synthetic stochastic networks as the training set and take the remaining 90% of the collected networks as the testing set.
Dataset Splits No The paper states 'we select 10% of the real-life networks to construct synthetic stochastic networks as the training set and take the remaining 90% of the collected networks as the testing set.' It does not explicitly mention a separate validation set.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x, CUDA x.x).
Experiment Setup Yes During the training process on synthetic graphs, we use a default propagation probability (p) of 0.8 and a maximal episode length (Tmax) of 120. In this work, we set the ratio of filtered user vertices and the height of pruned subtrees as 5% and 1, respectively.