Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors.
Md Abdul KadirGowtham Krishna AddluriDaniel SonntagPublished in: CoRR (2024)
Keyphrases
- parameter learning
- neural network
- bayesian networks
- structure learning
- generative model
- statistical learning
- conditional random fields
- maximum likelihood
- em algorithm
- parameter estimation
- approximate inference
- markov random field
- expectation maximization
- intrusion detection
- information theory
- probabilistic inference
- probabilistic model
- multilayer perceptron
- graphical models
- fuzzy neural network
- conditional independence
- training set