论文信息 - Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

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

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.

[1] Duen Horng Chau,et al. ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector , 2018, ECML/PKDD.

[2] Lujo Bauer,et al. Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition , 2016, CCS.

[3] Germán Ros,et al. CARLA: An Open Urban Driving Simulator , 2017, CoRL.

[4] Aleksander Madry,et al. Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[5] Logan Engstrom,et al. Synthesizing Robust Adversarial Examples , 2017, ICML.

[6] Chenxi Liu,et al. Adversarial Attacks Beyond the Image Space , 2017, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7] Ryan P. Adams,et al. Motivating the Rules of the Game for Adversarial Example Research , 2018, ArXiv.

[8] Dan Boneh,et al. SentiNet: Detecting Physical Attacks Against Deep Learning Systems , 2018, ArXiv.