A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference.
Sanghyun HongYigitcan KayaIonut-Vlad ModoranuTudor DumitrasPublished in: ICLR (2021)
Keyphrases
- neural network
- neural nets
- countermeasures
- artificial neural networks
- back propagation
- neural network model
- malicious attacks
- bayesian inference
- multi layer
- adaptive neural
- adaptive learning
- adaptive fuzzy
- neural network is trained
- neural fuzzy
- training algorithm
- probabilistic inference
- fuzzy logic
- pattern recognition