13 citations · 31 across the 8 of their papers we have counts for
12 papers
Synthesizing Pareto-Optimal Interpretations for Black-Box Models
Hazem Torfah, Shetal Shah, Supratik Chakraborty +2
We present a new multi-objective optimization approach for synthesizing interpretations that "explain" the behavior of black-box machine learning models. Constructing human-underst…
Runtime Monitoring for Markov Decision Processes
Sebastian Junges, Hazem Torfah, Sanjit A. Seshia
We investigate the problem of monitoring partially observable systems with nondeterministic and probabilistic dynamics. In such systems, every state may be associated with a risk,…
Synthesizing Approximate Implementations for Unrealizable Specifications
Rayna Dimitrova, Bernd Finkbeiner, Hazem Torfah
The unrealizability of a specification is often due to the assumption that the behavior of the environment is unrestricted. In this paper, we present algorithms for synthesis in bo…
Approximate Automata for Omega-Regular Languages
Rayna Dimitrova, Bernd Finkbeiner, Hazem Torfah
Automata over infinite words, also known as omega-automata, play a key role in the verification and synthesis of reactive systems. The spectrum of omega-automata is defined by two…
Canonical Representations of k-Safety Hyperproperties
Bernd Finkbeiner, Lennart Haas, Hazem Torfah
Hyperproperties elevate the traditional view of trace properties form sets of traces to sets of sets of traces and provide a formalism for expressing information-flow policies. For…
Explainable Reactive Synthesis
Tom Baumeister, Bernd Finkbeiner, Hazem Torfah
Reactive synthesis transforms a specification of a reactive system, given in a temporal logic, into an implementation. The main advantage of synthesis is that it is automatic. The…