Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks.
Ginevra CarboneGuido SanguinettiLuca BortolussiPublished in: CoRR (2021)
Keyphrases
- application layer
- bayesian networks
- countermeasures
- multi layer
- multi agent
- malicious attacks
- maximum likelihood
- posterior probability
- bayesian estimation
- malicious users
- bayesian analysis
- fault tolerance
- bayesian decision
- single layer
- bayesian learning
- gaussian processes
- posterior distribution
- domain theory
- watermarking scheme
- ddos attacks
- bayesian inference
- missing data
- security threats
- pairwise
- decision theory
- java card
- intrusion detection
- data driven
- probability distribution