Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It.
Federico SicilianoLuca MaianoLorenzo PapaFederica BacciniIrene AmeriniFabrizio SilvestriPublished in: CoRR (2023)
Keyphrases
- data sets
- input data
- experimental data
- probabilistic model
- data quality
- computational model
- measured data
- data analysis
- test data
- high level
- database
- prior knowledge
- data sources
- knowledge discovery
- mathematical model
- simulation data
- predictive model
- data structure
- prior information
- raw data
- data collection
- image data
- probability distribution
- missing data
- object detection
- data warehouse
- statistical methods
- data points
- learning models
- news stories
- social media
- data streams
- objective function
- news corpus
- dimensional vector