Figure 1 shows the error analysis for three object detectors, namely, Faster-RCNN, YOLOv5, and DeTR.

Figure 1: R-Blur adds Gaussian noise to image (a) with the fixation point (red dot) to obtain (b).

Specifically, we randomly sample an example and adopt a first-order procedure to approximate the Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients.

Guided by this theory, we propose an effective approach to improve ensemble adversarial defense, named interactive global adversarial training (iGA T).

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.