【论文阅读】Knockoff Nets: Stealing Functionality of Black-Box Models(2019)

在这里插入图片描述

摘要

Machine Learning (ML) models(机器学习模型) are increasingly(越来越多) deployed(部署) in the wild to perform(执行) a wide range of tasks(广泛的任务).
In this work, we ask to what extent(多大程度) can an adversary(对手) steal functionality(窃取功能) of such "victim’’ models based solely(仅基于) on blackbox interactions(黑箱交互): image in(图像输入), predictions out(预测输出).
In contrast to prior work(与之前的工作相反), we study complex victim blackbox models(复杂的受害者黑箱模型), and an adversary lacking knowledge of train/test data used by the model(缺乏模型使用的训练/测试数据), its internals(其内部), and semantics(语义) over model outputs(模型输出).
We formulate(表述) model functionality stealing(模型功能窃取) as a two-step approach(两步方法): (i) querying(查询) a set of(一组) input images(输入图像) to the blackbox model(黑盒模型) to obtain predictions(获得预测); and (ii) training a "knockoff’’ with queried image-prediction pairs(查询图像预测对).
We make multiple remarkable observations(多个显著的观察): (a) querying random images(查询随机图像) from a different distribution(从不同的分布中) than that of the blackbox training data(黑箱训练数

评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

Bosenya12

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值