Honggang Yu (University of Florida), Kaichen Yang (University of Florida), Teng Zhang (University of Central Florida), Yun-Yun Tsai (National Tsing Hua University), Tsung-Yi Ho (National Tsing Hua University), Yier Jin (University of Florida)

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

UIScope: Accurate, Instrumentation-free, and Visible Attack Investigation for GUI...

Runqing Yang (Zhejiang University), Shiqing Ma (Rutgers University), Haitao Xu (Arizona State University), Xiangyu Zhang (Purdue University), Yan Chen (Northwestern University)

Read More

Not All Coverage Measurements Are Equal: Fuzzing by Coverage...

Yanhao Wang (Institute of Software, Chinese Academy of Sciences), Xiangkun Jia (Pennsylvania State University), Yuwei Liu (Institute of Software, Chinese Academy of Sciences), Kyle Zeng (Arizona State University), Tiffany Bao (Arizona State University), Dinghao Wu (Pennsylvania State University), Purui Su (Institute of Software, Chinese Academy of Sciences)

Read More

Packet-Level Signatures for Smart Home Devices

Rahmadi Trimananda (University of California, Irvine), Janus Varmarken (University of California, Irvine), Athina Markopoulou (University of California, Irvine), Brian Demsky (University of California, Irvine)

Read More

A Practical Approach for Taking Down Avalanche Botnets Under...

Victor Le Pochat (imec-DistriNet, KU Leuven), Tim Van hamme (imec-DistriNet, KU Leuven), Sourena Maroofi (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG), Tom Van Goethem (imec-DistriNet, KU Leuven), Davy Preuveneers (imec-DistriNet, KU Leuven), Andrzej Duda (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG), Wouter Joosen (imec-DistriNet, KU Leuven), Maciej Korczyński (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG)

Read More