English List

收集常用的学术术语以及优秀的英语表达

学术术语

• deep neural networks (DNN) 深度神经网络
• Membership Inference Attacks (MIA) 成员推理攻击
• high True Positive Rates (TPR) in the low False Positive Rate (FPR) 低FPR前提下实现高TPR（现有的成员推理攻击的基本条件）
• pre-trained foundation models 预训练基础模型
• privacy backdoor 隐私后门
• fragile 脆弱

英语表达

• raises concerns about privacy and security 引发了对隐私与安全的担忧
• which allows adversaries to determine whether a specific data point was part of a model’s training dataset. 这句是对成员推理攻击的一个结束
• Unfortunately, recent studies have found that these models can memorize their training data to a large extent, compromising the privacy of participants in the training dataset. 表达模型对于数据的记忆能力而且侵犯个人隐私
• One prominent category of privacy attacks against machine learning is the so-called membership inference attack (Shokri et al., 2017; Yeom et al., 2018), where the adversary aims to infer the participation of an individual in the target model’s training set. 对于成员推理攻击的定义