Defending Elections against Malicious Spread of Misinformation

Authors: Bryan Wilder, Yevgeniy Vorobeychik2213-2220

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results confirm that our algorithms provide nearoptimal defender strategies and showcase variations in the difficulty of defending elections depending on the resources and knowledge available to the defender. Our experiments use the Yahoo webscope dataset (Yahoo 2007).
Researcher Affiliation Academia 1Center for Artificial Intelligence in Society, University of Southern California, bwilder@usc.edu 2Department of Computer Science & Engineering, Washington University in St. Louis, yvorobeychik@wustl.edu
Pseudocode Yes Algorithm 1 FPLT(ϵ) and Algorithm 2 Online Gradient(η, α, T, ka) are provided.
Open Source Code No No concrete statement or link regarding the availability of the methodology's source code is provided.
Open Datasets Yes Our experiments use the Yahoo webscope dataset (Yahoo 2007).
Dataset Splits No The paper mentions 'train', 'validation', and 'test' in the context of the problem but does not specify the actual data splits used for its experiments with exact percentages or sample counts.
Hardware Specification No No specific hardware details (e.g., CPU, GPU models, memory, or cloud instance types) are provided for the experimental setup.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python version, library versions) are mentioned.
Experiment Setup Yes We use T = 50 iterations with η = 0.05. Each propagation probability is drawn uniformly at random from [0, 0.2] for each player. Each voter s preference is also drawn uniformly at random.