In:
Proceedings of the VLDB Endowment, Association for Computing Machinery (ACM), Vol. 16, No. 12 ( 2023-08), p. 3942-3945
Abstract:
Recent works explore several attacks against Machine-Learning-as-a-Service (MLaaS) platforms (e.g., the model stealing attack), allegedly posing potential real-world threats beyond viability in laboratories. However, hampered by model-type-sensitive , most of the attacks can hardly break mainstream real-world MLaaS platforms. That is, many MLaaS attacks are designed against only one certain type of model, such as tree models or neural networks. As the black-box MLaaS interface hides model type info, the attacker cannot choose a proper attack method with confidence, limiting the attack performance. In this paper, we demonstrate a system, named Sniffer, that is capable of making model-type-sensitive attacks "great again" in real-world applications. Specifically, Sniffer consists of four components: Generator, Querier, Probe, and Arsenal. The first two components work for preparing attack samples. Probe, as the most characteristic component in Sniffer, implements a series of self-designed algorithms to determine the type of models hidden behind the black-box MLaaS interfaces. With model type info unraveled, an optimum method can be selected from Arsenal (containing multiple attack methods) to accomplish its attack. Our demonstration shows how the audience can interact with Sniffer in a web-based interface against five mainstream MLaaS platforms.
Type of Medium:
Online Resource
ISSN:
2150-8097
DOI:
10.14778/3611540.3611591
Language:
English
Publisher:
Association for Computing Machinery (ACM)
Publication Date:
2023
detail.hit.zdb_id:
2478691-3
Permalink