Detection as Regression: Certified Object Detection by Median Smoothing

Abstract

Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive. This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Then, to enable certified regression, where standard mean smoothing fails, we propose median smoothing, which is of independent interest. We obtain the first model-agnostic, training-free, and certified defense for object detection against ${\ell }_2$-bounded attacks. The code for all experiments in the paper is available at http://github.com/Ping-C/CertifiedObjectDetection .

References in corpus (14)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Certified Defenses against Adversarial Examples
• Robust Physical-World Attacks on Deep Learning Models
• Efficient Neural Network Robustness Certification with General Activation Functions
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
• Semidefinite relaxations for certifying robustness to adversarial examples
• Physical Adversarial Examples for Object Detectors
• Robust Adversarial Perturbation on Deep Proposal-based Models
• (De)Randomized Smoothing for Certifiable Defense against Patch Attacks
• Branch and Bound for Piecewise Linear Neural Network Verification
• Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches