Litcius/Paper detail

SEAT

Zhanyuan Zhang, Yizheng Chen, David Wagner

202133 citationsDOIOpen Access PDF

Abstract

Given black-box access to the prediction API, model extraction attacks can steal the functionality of models deployed in the cloud. In this paper, we introduce the SEAT detector, which detects black-box model extraction attacks so that the defender can terminate malicious accounts. SEAT has a similarity encoder trained by adversarial training. Using the similarity encoder, SEAT detects accounts that make queries that indicate a model extraction attack in progress and cancels these accounts. We evaluate our defense against existing model extraction attacks and against new adaptive attacks introduced in this paper. Our results show that even against adaptive attackers, SEAT increases the cost of model extraction attacks by 3.8 times to 16 times.

Topics & Concepts

Computer scienceSimilarity (geometry)EncoderCloud computingDetectorComputer securityBlack boxArtificial intelligenceReal-time computingData miningOperating systemTelecommunicationsImage (mathematics)Adversarial Robustness in Machine LearningNetwork Security and Intrusion DetectionAnomaly Detection Techniques and Applications