LATIDIA · Ciberseguridad
Backdoor I2I: ataques de backdoor contra tareas de imagen a imagen
arXiv:2407.10445v2 Tipo de anuncio: sustitución cruzada Resumen: Con el rápido desarrollo de la tecnología de aprendizaje profundo, las redes de imagen a imagen (I2I) basadas en aprendizaje profundo se han convertido en la opción predominante para tareas de I2I como im
WhatsApp ↗Telegram ↗
La noticia
arXiv:2407.10445v2 Announce Type: replace-cross Abstract: With the rapid development of deep learning technology, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks like image super-resolution and denoising. Despite their remarkable performance, the security of I2I networks has not been thoroughly investigated. While some studies have probed their susceptibility to adversarial attacks, none have explored the backdoor attack against I2I networks, which is a more stealthy and severe threat. In this work, for the first time, we comprehensively investigate the vulnerability of I2I networks to backdoor attacks. We propose a backdoor attack against I2I tasks, where the backdoored I2I network behaves normally on clean input images, yet