Aditya Nori

Learn More
Systems of weighted constraints are a natural formalism for many emerging tasks in program analysis and verification. Such systems include both hard and soft constraints: the desired solution must satisfy the hard constraints while optimizing the objectives expressed by the soft constraints. Existing techniques for solving such constraint systems sacrifice(More)
Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We(More)
  • 1