Visible to the public Defending Against Model Stealing Attacks With Adaptive Misinformation

TitleDefending Against Model Stealing Attacks With Adaptive Misinformation
Publication TypeConference Paper
Year of Publication2020
AuthorsKariyappa, S., Qureshi, M. K.
Conference Name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Date PublishedJune 2020
PublisherIEEE
ISBN Number978-1-7281-7168-5
KeywordsAdaptation models, Adaptive Misinformation, Adversary Models, attacker, attacker clone model, black-box query access, clone model, Cloning, Computational modeling, Data models, deep neural networks, Human Behavior, labeled dataset, learning (artificial intelligence), Metrics, model stealing attacks, neural nets, OOD queries, out-of-distribution inputs, Perturbation methods, Predictive models, pubcrawl, query processing, resilience, Resiliency, Scalability, security, security of data, training dataset
Abstract

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such attacks are typically carried out by querying the target model using inputs that are synthetically generated or sampled from a surrogate dataset to construct a labeled dataset. The adversary can use this labeled dataset to train a clone model, which achieves a classification accuracy comparable to that of the target model. We propose "Adaptive Misinformation" to defend against such model stealing attacks. We identify that all existing model stealing attacks invariably query the target model with Out-Of-Distribution (OOD) inputs. By selectively sending incorrect predictions for OOD queries, our defense substantially degrades the accuracy of the attacker's clone model (by up to 40%), while minimally impacting the accuracy (\textbackslashtextless; 0.5%) for benign users. Compared to existing defenses, our defense has a significantly better security vs accuracy trade-off and incurs minimal computational overhead.

URLhttps://ieeexplore.ieee.org/document/9157021
DOI10.1109/CVPR42600.2020.00085
Citation Keykariyappa_defending_2020