XAI-Attack: Utilizing Explainable AI to Find Incorrectly Learned Patterns for Black-Box Adversarial Example Creation.
Markus BayerMarkus NeiczerMaximilian SamsingerBjörn BuchholdChristian ReuterPublished in: LREC/COLING (2024)
Keyphrases
- black box
- black boxes
- artificial intelligence
- white box
- rule extraction
- frequent patterns
- intelligent systems
- expert systems
- knowledge representation
- data mining techniques
- test cases
- multi agent
- integration testing
- white box testing
- case based reasoning
- machine learning
- pattern mining
- countermeasures
- hybrid systems
- ai systems
- decision trees