BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918528460783616 |
|---|---|
| author | Wu, Jia Pan, Yu Yang, Junjun Du, Yi |
| author_facet | Wu, Jia Pan, Yu Yang, Junjun Du, Yi |
| contents | Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing threats through visual inspection or feature analysis, we introduce BadBlocks-a novel, lightweight, and highly covert attack that challenges these safeguards. By selectively poisoning specific blocks within the UNet architecture while keeping other components intact, BadBlocks requires only 30% of the computational resources and 20% of the GPU time of conventional attacks, effectively democratizing backdoor injection on consumer-grade GPUs. Empirical evaluations demonstrate that BadBlocks achieves a high attack success rate with negligible perceptual quality loss, while successfully bypassing state-of-the-art defenses, particularly attention-based detection frameworks. Layer-level ablation studies further confirm that backdoor mapping does not require full-network fine-tuning, revealing the disparate vulnerability of different neural layers. Overall, BadBlocks significantly lowers the barrier for executing backdoor attacks, presenting a critical security risk. Our code is available at: https://github.com/paoche11/BadBlocks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03221 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models Wu, Jia Pan, Yu Yang, Junjun Du, Yi Cryptography and Security Computer Vision and Pattern Recognition Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing threats through visual inspection or feature analysis, we introduce BadBlocks-a novel, lightweight, and highly covert attack that challenges these safeguards. By selectively poisoning specific blocks within the UNet architecture while keeping other components intact, BadBlocks requires only 30% of the computational resources and 20% of the GPU time of conventional attacks, effectively democratizing backdoor injection on consumer-grade GPUs. Empirical evaluations demonstrate that BadBlocks achieves a high attack success rate with negligible perceptual quality loss, while successfully bypassing state-of-the-art defenses, particularly attention-based detection frameworks. Layer-level ablation studies further confirm that backdoor mapping does not require full-network fine-tuning, revealing the disparate vulnerability of different neural layers. Overall, BadBlocks significantly lowers the barrier for executing backdoor attacks, presenting a critical security risk. Our code is available at: https://github.com/paoche11/BadBlocks. |
| title | BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03221 |