Training deep neural networks often forces users to work in a distributed or outsourced setting, accompanied with privacy concerns. Split learning aims to address this concern by distributing the model among a client and a server. The scheme supposedly provides privacy, since the server cannot see the clients' models and inputs. We show that this is not true via two novel attacks. (1) We show that an honest-but-curious split learning server, equipped only with the knowledge of the client neural network architecture, can recover the input samples and obtain a functionally similar model to the client model, without being detected. (2) We show that if the client keeps hidden only the output layer of the model to "protect" the private labels, the honest-but-curious server can infer the labels with perfect accuracy. We test our attacks using various benchmark datasets and against proposed privacy-enhancing extensions to split learning. Our results show that plaintext split learning can pose serious risks, ranging from data (input) privacy to intellectual property (model parameters), and provide no more than a false sense of security.
翻译:培训深层神经网络往往迫使用户在分布式或外包环境下工作,同时附带隐私问题。 分散学习的目的是通过在客户和服务器之间分配模型来解决这一问题。 计划据称提供了隐私, 因为服务器无法看到客户的模式和输入。 我们通过两次新式袭击表明,这是不真实的。 (1) 我们显示,一个只配备客户神经网络结构知识的诚实但又充满怀疑的分离学习服务器,能够回收输入样本,获得与客户模式功能相似的模型,而不被发现。 (2) 我们显示,如果客户只隐藏“保护”私人标签的模型输出层,诚实但可靠的服务器可以精确地推断标签。 我们用各种基准数据集测试我们的攻击,并对照拟议的增强隐私扩展来进行分离学习。 我们的结果表明,纯化的分离学习可能带来严重风险,从数据(投入式)隐私到知识产权(模范参数)不等,并且只能提供虚假的安全感。