Metrics
29 Record Views
Conference proceeding
Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp.975-976
Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (Orlando, Florida, USA, 03/16/2024–03/21/2024)
03/16/2024
Web of Science ID: WOS:001239375400278
Abstract
In Virtual Reality (VR), adversarial attack remains a significant se-curity threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a no-ticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities.
Related links
Details
- Title
- Diffusion Attack
- Publication Details
- 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp.975-976
- Resource Type
- Conference proceeding
- Conference
- Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (Orlando, Florida, USA, 03/16/2024–03/21/2024)
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Number of pages
- 2
- Copyright
- © IEEE, 2024
- Identifiers
- WOS:001239375400278; 99380579481906600
- Academic Unit
- Mechanical Engineering; Hal Marcus College of Science and Engineering
- Language
- English