Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting
This addresses a security problem for machine learning model owners by enabling more efficient model stealing attacks, though it is incremental as it builds on existing cooperative game frameworks.
The paper tackles data-free model stealing in a hard label setting by proposing Query Efficient Data Generation (QEDG), which uses loss functions and query-free sample augmentation to generate samples aligning with the target model's decision boundary, achieving better performance with fewer queries than state-of-the-art methods on real MLaaS scenarios and five datasets.
Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's predictions for generated samples. Once the substitute model closely approximates the behavior of the target model, attackers can exploit its white-box characteristics for subsequent malicious activities, such as adversarial attacks. Existing methods within cooperative game frameworks often produce samples with high confidence for the prediction of the substitute model, which makes it difficult for the substitute model to replicate the behavior of the target model. This paper presents a new data-free model stealing approach called Query Efficient Data Generation (\textbf{QEDG}). We introduce two distinct loss functions to ensure the generation of sufficient samples that closely and uniformly align with the target model's decision boundary across multiple classes. Building on the limitation of current methods, which typically yield only one piece of supervised information per query, we propose the query-free sample augmentation that enables the acquisition of additional supervised information without increasing the number of queries. Motivated by theoretical analysis, we adopt the consistency rate metric, which more accurately evaluates the similarity between the substitute and target models. We conducted extensive experiments to verify the effectiveness of our proposed method, which achieved better performance with fewer queries compared to the state-of-the-art methods on the real \textbf{MLaaS} scenario and five datasets.