MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense.
Sailik SenguptaTathagata ChakrabortiSubbarao KambhampatiPublished in: AAAI Workshops (2018)
Keyphrases
- neural nets
- moving target defense
- security threats
- security mechanisms
- security problems
- computer security
- security issues
- cyber attacks
- security protocols
- feed forward
- java card
- security measures
- countermeasures
- information security
- security vulnerabilities
- denial of service attacks
- security risks
- neural network
- back propagation
- chosen plaintext
- security requirements
- access control
- biometric template
- artificial neural networks
- learning tasks
- deep architectures
- cryptographic protocols
- feature selection
- single layer
- computer networks
- key management
- malicious nodes
- smart card
- intrusion detection
- artificial intelligence
- learning algorithm