Cloud-based Machine Learning as a Service (MLaaS) is gradually gaining acceptance as a reliable solution to various real-life scenarios. These services typically utilize Deep Neural Networks (DNNs) to perform classification and detection tasks and are accessed through Application Programming Interfaces (APIs). Unfortunately, it is possible for an adversary to steal models from cloud-based platforms, even with black-box constraints, by repeatedly querying the public prediction API with malicious inputs. In this paper, we introduce an effective and efficient black-box attack methodology that extracts largescale DNN models from cloud-based platforms with near-perfect performance. In comparison to existing attack methods, we significantly reduce the number of queries required to steal the target model by incorporating several novel algorithms, including active learning, transfer learning, and adversarial attacks. During our experimental evaluations, we validate our proposed model for conducting theft attacks on various commercialized MLaaS platforms including two Microsoft Custom Vision APIs (Microsoft Traffic Recognition API and Microsoft Flower Recognition API), the Face++ Emotion Recognition API, the IBM Watson Visual Recognition API, Google AutoML API, and the Clarifai Safe for Work (NSFW) API. Our results demonstrate that the proposed method can easily reveal/steal large-scale DNN models from these cloud platforms. Further, the proposed attack method can also be used to accurately evaluates the robustness of DNN based MLaaS image classifiers against theft attacks.

View More Papers

Poseidon: Mitigating Volumetric DDoS Attacks with Programmable Switches

Menghao Zhang (Tsinghua University), Guanyu Li (Tsinghua University), Shicheng Wang (Tsinghua University), Chang Liu (Tsinghua University), Ang Chen (Rice University),...

Read More

Let's Revoke: Scalable Global Certificate Revocation

Trevor Smith (Brigham Young University), Luke Dickenson (Brigham Young University), Kent Seamons (Brigham Young University)

Read More

Secure Sublinear Time Differentially Private Median Computation

Jonas Böhler (SAP Security Research), Florian Kerschbaum (University of Waterloo)

Read More

When Match Fields Do Not Need to Match: Buffered...

Jiahao Cao (Tsinghua University; George Mason University), Renjie Xie (Tsinghua University), Kun Sun (George Mason University), Qi Li (Tsinghua University),...

Read More