Area of research
Artificial Intelligence · Computational Theory and Mathematics
Research interest
Research interests include Computer science, Artificial neural network, Artificial intelligence, Scalability, Robustness (evolution), and Correctness.
Shield Synthesis for LTL Modulo Theories
Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing
Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace
Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networks
OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks
Verifying Generalization in Deep Learning
RoMA: A Method for Neural Network Robustness Measurement and Assessment
veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection System
Towards a Certified Proof Checker for Deep Neural Network Verification
On applying residual reasoning within neural network verification
Enhancing Deep Reinforcement Learning with Scenario-Based Modeling
Tighter Abstract Queries in Neural Network Verification
Neural Network Robustness as a Verification Property: A Principled Case Study
An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks
Efficient Neural Network Analysis with Sum-of-Infeasibilities
Neural Network Verification Using Residual Reasoning
Minimal Multi-Layer Modifications of Deep Neural Networks
Scenario-assisted Deep Reinforcement Learning
An SMT-Based Approach for Verifying Binarized Neural Networks
Global optimization of objective functions represented by ReLU networks
Augmenting Deep Neural Networks with Scenario-Based Guard Rules
Verifying Recurrent Neural Networks Using Invariant Inference
The Marabou Framework for Verification and Analysis of Deep Neural Networks
On-the-Fly Construction of Composite Events in Scenario-Based Modeling using Constraint Solvers