Transferable Adversarial Attacks for Image and Video Object Detection

In this project, we aims at proposing an Unified and Efficient Adversary (UEA) for object detection. UEA can simultaneously attack two kinds of representative object detectors: proposal based detectors like Faster-rcnn, and regression based detector like SSD. In addition, UEA use a generative mechanism to generate adversarial examples, therefore, can efficiently perturbs all the frames in a video. Thus, UEA can attack both the image and video object detection. Next, we will show more results of UEA to attack SSD300 and Faster-RCNN on video data of ImageNet VID dataset.