Practical Black-Box Attacks against Machine Learning
Top Cited Papers
- 2 April 2017
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 506-519
- https://doi.org/10.1145/3052973.3053009
Abstract
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include having malicious content like malware identified as legitimate or controlling vehicle behavior. Yet, all existing adversarial example attacks require knowledge of either the model internals or its training data. We introduce the first practical demonstration of an attacker controlling a remotely hosted DNN with no such knowledge. Indeed, the only capability of our black-box adversary is to observe labels given by the DNN to chosen inputs. Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN. We use the local substitute to craft adversarial examples, and find that they are misclassified by the targeted DNN. To perform a real-world and properly-blinded evaluation, we attack a DNN hosted by MetaMind, an online deep learning API. We find that their DNN misclassifies 84.24% of the adversarial examples crafted with our substitute. We demonstrate the general applicability of our strategy to many ML techniques by conducting the same attack against models hosted by Amazon and Google, using logistic regression substitutes. They yield adversarial examples misclassified by Amazon and Google at rates of 96.19% and 88.94%. We also find that this black-box attack strategy is capable of evading defense strategies previously found to make adversarial example crafting harder.Keywords
Other Versions
Funding Information
- Army Research Laboratory (W911NF-13-2-0045)
This publication has 7 references indexed in Scilit:
- Accessorize to a CrimePublished by Association for Computing Machinery (ACM) ,2016
- The Limitations of Deep Learning in Adversarial SettingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Practical Evasion of a Learning-Based Classifier: A Case StudyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012
- Adversarial machine learningPublished by Association for Computing Machinery (ACM) ,2011
- Can machine learning be secure?Published by Association for Computing Machinery (ACM) ,2006
- Random sampling with a reservoirACM Transactions on Mathematical Software, 1985