Membership Inference Attacks Against Object Detection Models
arXiv:2001.04011
Abstract
Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records are used in the training. To attack the object detection model, we devise a novel method named as called a canvas method, in which predicted bounding boxes are drawn on an empty image for the attack model input. Based on the experiments, we successfully reveal the membership status of privately sensitive data trained using one-stage and two-stage detection models. We then propose defense strategies and also conduct a transfer attack between the models and datasets. Our results show that object detection models are also vulnerable to inference attacks like other models.
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Deep Learning with Differential Privacy
- Understanding Membership Inferences on Well-Generalized Learning Models
- Synthetic Data for Text Localisation in Natural Images
- Why Random Reshuffling Beats Stochastic Gradient Descent
- Transferable Adversarial Attacks for Image and Video Object Detection
- Machine Learning with Membership Privacy using Adversarial Regularization