154 citations · 639 across the 138 of their papers we have counts for
9 papers · 1 filter
Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks
Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
Function approximation has enabled remarkable advances in applying reinforcement learning (RL) techniques in environments with high-dimensional inputs, such as images, in an end-to…
Attacking Shortest Paths by Cutting Edges
Benjamin A. Miller, Zohair Shafi, Wheeler Ruml +3
Identifying shortest paths between nodes in a network is a common graph analysis problem that is important for many applications involving routing of resources. An adversary that c…
A Visual Active Search Framework for Geospatial Exploration
Anindya Sarkar, Michael Lanier, Scott Alfeld +4
Many problems can be viewed as forms of geospatial search aided by aerial imagery, with examples ranging from detecting poaching activity to human trafficking. We model this class…
Reward Delay Attacks on Deep Reinforcement Learning
Anindya Sarkar, Jiarui Feng, Yevgeniy Vorobeychik +2
Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by…
Manipulating Elections by Changing Voter Perceptions
Junlin Wu, Andrew Estornell, Lecheng Kong +1
The integrity of elections is central to democratic systems. However, a myriad of malicious actors aspire to influence election outcomes for financial or political benefit. A commo…
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Junlin Wu, Yevgeniy Vorobeychik
Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations. Recent efforts that have…