Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
Xu, Qiongkai, He, Xuanli, Lyu, Lingjuan, Qu, Lizhen, Haffari, Gholamreza
–arXiv.org Artificial Intelligence
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models. Although published as black-box APIs, the valuable models behind these services are still vulnerable to imitation attacks. Recently, a series of works have demonstrated that attackers manage to steal or extract the victim models. Nonetheless, none of the previous stolen models can outperform the original black-box APIs. In this work, we conduct unsupervised domain adaptation and multi-victim ensemble to showing that attackers could potentially surpass victims, which is beyond previous understanding of model extraction. Extensive experiments on both benchmark datasets and real-world APIs validate that the imitators can succeed in outperforming the original black-box models on transferred domains. We consider our work as a milestone in the research of imitation attack, especially on NLP APIs, as the superior performance could influence the defense or even publishing strategy of API providers.
arXiv.org Artificial Intelligence
Sep-4-2022
- Country:
- North America > United States
- Europe
- Czechia > Prague (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Transportation > Air (1.00)
- Information Technology > Security & Privacy (1.00)
- Technology: