8 papers
Differential Privacy for Markov Chain State Trajectories
Alexander Benvenuti, Matthew Hale
Data-driven systems may require state trajectories of Markov chains to function because these trajectories contain information that is useful to the system, e.g., a product's credi…
End-to-End Differential Privacy in Training Deep Neural Network Classifiers
Huaiyuan Rao, Calvin Hawkins, Alexander Benvenuti +1
Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from the parameters of the result…
Deception in Linear-Quadratic Control
Yerin Kim, Haosheng Zhou, Alexander Benvenuti +2
Systems operating in adversarial environments may inadvertently leak sensitive information to adversaries. To address this challenge, we revisit the linear-quadratic control framew…
Differential Privacy for Symbolic Trajectories via the Permute-and-Flip Mechanism
Alexander Benvenuti, Huaiyuan Rao, Matthew Hale
Privacy techniques have been developed for data-driven systems, but systems with non-numeric data cannot use typical noise-adding techniques. Therefore, we develop a new mechanism…
Differentially Private Data-Driven Markov Chain Modeling
Alexander Benvenuti, Brandon Fallin, Calvin Hawkins +4
Markov chains model a wide range of user behaviors. However, generating accurate Markov chain models requires substantial user data, and sharing these models without privacy protec…
Deceptive Sequential Decision-Making via Regularized Policy Optimization
Yerin Kim, Alexander Benvenuti, Bo Chen +5
Autonomous systems are increasingly expected to operate in the presence of adversaries, though adversaries may infer sensitive information simply by observing a system. Therefore,…