Best-Effort Adversarial Approximation of Black-Box Malware Classifiers
This addresses security vulnerabilities in malware detection systems by showing how adversaries can effectively steal model functionality even with minimal access.
The paper tackles the problem of approximating black-box malware classifiers when adversaries only have access to prediction labels, achieving 90-92% accurate substitutes with 90% prediction agreement against two different black-box classifiers.
An adversary who aims to steal a black-box model repeatedly queries the model via a prediction API to learn a function that approximates its decision boundary. Adversarial approximation is non-trivial because of the enormous combinations of model architectures, parameters, and features to explore. In this context, the adversary resorts to a best-effort strategy that yields the closest approximation. This paper explores best-effort adversarial approximation of a black-box malware classifier in the most challenging setting, where the adversary's knowledge is limited to a prediction label for a given input. Beginning with a limited input set for the black-box classifier, we leverage feature representation mapping and cross-domain transferability to approximate a black-box malware classifier by locally training a substitute. Our approach approximates the target model with different feature types for the target and the substitute model while also using non-overlapping data for training the target, training the substitute, and the comparison of the two. We evaluate the effectiveness of our approach against two black-box classifiers trained on Windows Portable Executables (PEs). Against a Convolutional Neural Network (CNN) trained on raw byte sequences of PEs, our approach achieves a 92% accurate substitute (trained on pixel representations of PEs), and nearly 90% prediction agreement between the target and the substitute model. Against a 97.8% accurate gradient boosted decision tree trained on static PE features, our 91% accurate substitute agrees with the black-box on 90% of predictions, suggesting the strength of our purely black-box approximation.