papers AI Learner
The Github is limit! Click to go to the new site.

Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

2019-04-18
Cory Cornelius, Shang-Tse Chen, Jason Martin, Duen Horng Chau

Abstract

In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios. We describe how we use CARLA, a realistic urban driving simulator, to create these scenarios, and how we use ShapeShifter to generate content-preserving attacks against those scenarios.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.12622

PDF

http://arxiv.org/pdf/1904.12622


Similar Posts

Comments