most cited"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

27 citations · 84 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG202018 cited

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

Sangdon Park, Osbert Bastani, Nikolai Matni +1

We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i…

cs.AI201927 cited

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

Himabindu Lakkaraju, Osbert Bastani

As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniq…

eess.SY201924 cited

MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding

Wenbo Zhang, Osbert Bastani, Vijay Kumar

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails t…

eess.SY20197 cited

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

Shuo Li, Osbert Bastani

This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known…

cs.SE20193 cited

PolyDroid: Learning-Driven Specialization of Mobile Applications

Brian Heath, Neelay Velingker, Osbert Bastani +1

The increasing prevalence of mobile apps has led to a proliferation of resource usage scenarios in which they are deployed. This motivates the need to specialize mobile apps based…

cs.LG20195 cited

Learning Neurosymbolic Generative Models via Program Synthesis

Halley Young, Osbert Bastani, Mayur Naik

Significant strides have been made toward designing better generative models in recent years. Despite this progress, however, state-of-the-art approaches are still largely unable t…