CAMH: Advancing Model Hijacking Attack in Machine Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915072149815296 |
|---|---|
| author | He, Xing Chen, Jiahao Pu, Yuwen Li, Qingming Zhou, Chunyi Wu, Yingcai Li, Jinbao Ji, Shouling |
| author_facet | He, Xing Chen, Jiahao Pu, Yuwen Li, Qingming Zhou, Chunyi Wu, Yingcai Li, Jinbao Ji, Shouling |
| contents | In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner's knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task's performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13741 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CAMH: Advancing Model Hijacking Attack in Machine Learning He, Xing Chen, Jiahao Pu, Yuwen Li, Qingming Zhou, Chunyi Wu, Yingcai Li, Jinbao Ji, Shouling Cryptography and Security In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner's knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task's performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task. |
| title | CAMH: Advancing Model Hijacking Attack in Machine Learning |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2408.13741 |