When Should You Defend Your Classifier - A Game-theoretical Analysis of Countermeasures against Adversarial Examples.
Maximilian SamsingerFlorian MerklePascal SchöttleTomás PevnýPublished in: CoRR (2021)
Keyphrases
- countermeasures
- theoretical analysis
- training examples
- information security
- power analysis
- nash equilibrium
- support vector
- java card
- training data
- sample selection bias
- training samples
- cyber attacks
- game play
- computer games
- game theory
- support vector machine
- training set
- case study
- minimax search
- machine learning
- differential power analysis
- security issues
- game playing
- video games
- active learning
- multi agent
- reinforcement learning
- learning algorithm