Research
Privacy-Preserving Object Detection for Vision Transformer-Based Models
arXiv:2608.20712v1 Announce Type: cross Abstract: We propose a novel object detection method that enables us to protect sensitive visual information of test images. Previous studies considering visual
arXiv:2608.20712v1 Announce Type: cross Abstract: We propose a novel object detection method that enables us to protect sensitive visual information of test images. Previous studies considering visual information protection focus on image classification tasks. This paper proposes an object detection method using perceptual encryption for the first time. The proposed method can achieve almost the same accuracy as that of models without any protection by utilizing the embedding structure of the Vision Transformer (ViT) and a domain adaptation technique with keys. In experiments, the effectiveness of the proposed method is verified in terms of accuracy and visual protection under the use of ViTdet, which is a ViT-based object detection model.
Related
- Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
- SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models
- Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation
Source: arXiv cs.CV | 2026-08-24