RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy.
Adnan Siraj RakinLi YangJingtao LiFan YaoChaitali ChakrabartiYu CaoJae-sun SeoDeliang FanPublished in: CoRR (2021)
Keyphrases
- neural network
- highly accurate
- high accuracy
- computationally efficient
- sufficiently accurate
- computational cost
- classification accuracy
- low error
- artificial neural networks
- binary representation
- neural network model
- block cipher
- countermeasures
- error analysis
- network architecture
- roc curve
- speech recognition
- prediction accuracy
- pattern recognition