{"type":"ScholarlyArticle","title":"SwiftThief: Enhancing Query Efficiency of Model Stealing by Contrastive Learning","authors":[{"name":"Jeonghyun Lee","slug":"jeonghyun-lee","given":"Jeonghyun","family":"Lee","affiliation":""},{"name":"Sungmin Han","slug":"sungmin-han","given":"Sungmin","family":"Han","affiliation":""},{"name":"Sangkyun Lee","slug":"sangkyun-lee","given":"Sangkyun","family":"Lee","affiliation":""}],"abstract":"Model-stealing attacks are emerging as a severe threat to AI-based services because an adversary can create models that duplicate the functionality of the black-box AI models inside the services with regular query-based access. To avoid detection or query costs, the model-stealing adversary must consider minimizing the number of queries to obtain an accurate clone model. To achieve this goal, we propose SwiftThief, a novel model-stealing framework that utilizes both queried and unqueried data to reduce query complexity. In particular, SwiftThief uses contrastive learning, a recent technique for representation learning. We formulate a new objective function for model stealing consisting of self-supervised (for abundant unqueried inputs from public datasets) and soft-supervised (for queried inputs) contrastive losses, jointly optimized with an output matching loss (for queried inputs). In addition, we suggest a new sampling strategy to prioritize rarely queried classes to improve attack performance. Our experiments proved that SwiftThief could significantly enhance the efficiency of model-stealing attacks compared to the existing methods, achieving similar attack performance using only half of the query budgets of the competing approaches. Also, SwiftThief showed high competence even when a defense was activated for the victims.","doi":"10.24963/ijcai.2024/47","url":"https://ijcai.org/proceedings/2024/47","pdf":"https://ijcai.org/proceedings/2024/0047.pdf","markdown":"https://ijcai.org/proceedings/2024/47.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/47","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":47,"pages":{"first":422,"last":430},"keywords":["AI Ethics, Trust, Fairness: ETF: Safety and robustness","Multidisciplinary Topics and Applications: MTA: Security and privacy"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}