Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots.
Xi XinGiles HookerFei HuangPublished in: CoRR (2024)
Keyphrases
- machine learning
- machine learning methods
- countermeasures
- trust evaluation
- multi agent
- learning systems
- malicious nodes
- trust model
- natural language processing
- data mining
- supervised learning
- information extraction
- data analysis
- computer science
- learning algorithm
- malicious attacks
- reputation systems
- traffic analysis
- network anomaly detection
- inductive learning
- machine learning algorithms
- support vector machine
- computer vision
- machine learning approaches
- knowledge acquisition
- security protocols
- text classification
- computational intelligence
- trust relationships
- decision trees
- artificial intelligence