53 citations · 85 across the 10 of their papers we have counts for
10 papers
Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations
Prithviraj Dasgupta
We consider the problem of learning to perform a task from demonstrations given by teachers or experts, when some of the experts' demonstrations might be adversarial and demonstrat…
Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning
Bryan Brandt, Prithviraj Dasgupta
We consider the problem of synthetically generating data that can closely resemble human decisions made in the context of an interactive human-AI system like a computer game. We pr…
A Comparison of State-of-the-Art Techniques for Generating Adversarial Malware Binaries
Prithviraj Dasgupta, Zachariah Osman
We consider the problem of generating adversarial malware by a cyber-attacker where the attacker's task is to strategically modify certain bytes within existing binary malware file…
Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers
Prithviraj Dasgupta, Joseph B. Collins, Michael McCarrick
We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class…
A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
Prithviraj Dasgupta, Joseph B. Collins
Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on…
Simultaneous Configuration Formation and Information Collection by Modular Robotic Systems
Ayan Dutta, Prithviraj Dasgupta
We consider the configuration formation problem in modular robotic systems where a set of singleton modules that are spatially distributed in an environment are required to assume…
Integrated Task and Motion Planning for Multiple Robots under Path and Communication Uncertainties
Bradley Woosley, Prithviraj Dasgupta
We consider a problem called task ordering with path uncertainty (TOP-U) where multiple robots are provided with a set of task locations to visit in a bounded environment, but the…
A Graph Isomorphism-based Decentralized Algorithm for Modular Robot Configuration Formation
Ayan Dutta, Prithviraj Dasgupta, Carl Nelson
We consider the problem of configuration formation in modular robot systems where a set of modules that are initially in different configurations and located at different locations…
A Multi-Agent Prediction Market based on Partially Observable Stochastic Game
Janyl Jumadinova, Prithviraj Dasgupta
We present a novel, game theoretic representation of a multi-agent prediction market using a partially observable stochastic game with information (POSGI). We then describe a corre…
Multi-sensor Information Processing using Prediction Market-based Belief Aggregation
Janyl Jumadinova, Prithviraj Dasgupta
We consider the problem of information fusion from multiple sensors of different types with the objective of improving the confidence of inference tasks, such as object classificat…