When adversarial attacks become interpretable counterfactual explanations.
Mathieu SerrurierFranck MamaletThomas FelLouis BéthuneThibaut BoissinPublished in: CoRR (2022)
Keyphrases
- countermeasures
- malicious attacks
- java card
- watermarking scheme
- malicious users
- data sets
- database
- multi agent
- generating explanations
- security protocols
- traffic analysis
- chosen plaintext
- digital image watermarking
- explanatory power
- security risks
- security threats
- cyber attacks
- image watermarking
- dos attacks
- smart card
- learning algorithm