Unleashing the Tiger: Inference Attacks on Split Learning
Autor: | Dario Pasquini, Massimo Bernaschi, Giuseppe Ateniese |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Cryptography and Security Computer science business.industry Process (engineering) Deep learning Inference Collaborative learning Computer security computer.software_genre Federated learning Machine Learning (cs.LG) State (computer science) Artificial intelligence Resource consumption business Cryptography and Security (cs.CR) Protocol (object-oriented programming) computer |
Zdroj: | CCS |
Popis: | We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and demonstrate its inherent insecurity by introducing general attack strategies targeting the reconstruction of clients' private training sets. More prominently, we show that a malicious server can actively hijack the learning process of the distributed model and bring it into an insecure state that enables inference attacks on clients' data. We implement different adaptations of the attack and test them on various datasets as well as within realistic threat scenarios. We demonstrate that our attack is able to overcome recently proposed defensive techniques aimed at enhancing the security of the split learning protocol. Finally, we also illustrate the protocol's insecurity against malicious clients by extending previously devised attacks for Federated Learning. To make our results reproducible, we made our code available at https://github.com/pasquini-dario/SplitNN_FSHA. ACM Conference on Computer and Communications Security 2021 (CCS21) |
Databáze: | OpenAIRE |
Externí odkaz: |