Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks.
Jialai WangZiyuan ZhangMeiqi WangHan QiuTianwei ZhangQi LiZongpeng LiTao WeiChao ZhangPublished in: CoRR (2023)
Keyphrases
- neural network
- block cipher
- countermeasures
- pattern recognition
- genetic algorithm
- artificial neural networks
- traffic analysis
- neural network model
- fuzzy logic
- back propagation
- s box
- feed forward
- neural nets
- advanced encryption standard
- training process
- fuzzy systems
- multi layer
- fault diagnosis
- network architecture
- risk management
- activation function
- rule extraction
- security protocols
- radial basis function
- security threats
- self organizing maps
- malicious attacks
- recommender systems