How to Leak a Secret and Reap the Rewards Too.
Vishal SaraswatSumit Kumar PandeyPublished in: LATINCRYPT (2014)
Keyphrases
- reinforcement learning
- multiarmed bandit
- markov decision processes
- information flow
- secret sharing scheme
- long term and short term
- multi armed bandits
- bandit problems
- private information
- neural network
- state space
- secret sharing
- secret information
- secret key
- free riding
- visual cryptography
- reward function
- multiscale
- machine learning
- secret data
- image quality
- learning algorithm