安全与密码学2017arxiv.org

Apple 在 macOS 10.12 中差分隐私实现的隐私损失

Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12

进阶 · 约 60 分钟读完前置知识：差分隐私基础、隐私预算与 ε 的含义、macOS 系统机制了解

读论文 HN 讨论

239HN 得分

47条评论

4次被评论区引用

2次投稿

导读

这篇论文分析了 Apple 在 macOS 10.12 中实现的差分隐私机制，发现其隐私预算（ε）会随使用时间不断累积增长，从而逐渐削弱隐私保证。作者指出 Apple 未公开说明隐私损失参数，用户难以据此做出知情选择，且缺乏透明度可能为 Apple 单方面滥用留下空间。

HN 关注点：Apple 隐私宣传与实际实现之间的差距，讨论焦点是隐私预算随时间累积是否意味着差分隐私保证被削弱，以及这种实现是否违背差分隐私透明性的初衷。

关键词　差分隐私Apple隐私预算macOS

HN 评论精选

这几条评论里：支持 1　质疑 2　补充 1

补充澄清论文实际发现：是隐私预算随使用累积，而非机制被绕过

我喜欢这项工作，但标题可能误导那些把“隐私损失”和“差分隐私”区分开的人。他们展示的是：随着使用 Apple 的实现，差分隐私参数会增长（随时间推移提供更弱的保证）。他们并没有证明能绕过该机制及其保证，只是说明 Apple 把实现设计成保证随持续使用而衰减（注：停止使用 Apple 产品后衰减即停止）。

frankmcsherry查看英文原文

While I like this work, the title may be misleading to people who think of "privacy loss" as something distinct from "differential privacy". What they show is that as you use Apple's implementation, the differential privacy parameter grows (providing weaker guarantees as time passes). They don't show that they can bypass the mechanism and it's guarantees, just that Apple has rigged the implementation to decay the guarantees as you continue to use it (note: decay stops if you stop using Apple stuffs).

质疑质疑隐私预算累积的实际影响是否真的大

所以现在 Apple 的隐私系统只是“比其他家聪明地更安全”，而不是“离谱地更安全”了。每天 16 听起来比 1 或 2 多很多，但这些数字意味着什么？16 应该是每天生成所有类型隐私数据时的理论上限。但 16 真的很多吗？累积到多高才能用于提取个人可靠信息？收集的信息不还是得关联到个人才有用吗？坦白说我从论文里无法判断这些。

simonh查看英文原文

So now Apple's privacy system is only stupidly more secure than everyone else's instead of absurdly more secure. So 16 per day sounds like a lot more than 1 or 2 per day, but what do these numbers mean? Presumably 16 per day is a theoretical maximum if you were to generate every kind of privacy related data ever day. But is 16 really a lot? How high would that have to cumulatively go in order to be useful for extracting reliable info on an individual? Wouldn't the info collected on an individual still have to be associated with them? Frankly I'm not really able to determine any of that from the paper.

质疑质疑长期持续收集数据与隐私保护的根本矛盾

有人能简单解释一下吗：像 Apple、Google 或 Microsoft 这样的“亲密”服务商，如何能在持续收集数据的情况下不最终损失隐私？

mirimir查看英文原文

Could someone please ELI5 how an "intimate" provider (such as Apple, Google or Microsoft) can collect any data ongoingly without eventual loss of privacy?

支持指出缺乏透明度违背差分隐私初衷并留下滥用空间

对我来说关键在于：1) 系统允许的隐私损失没有任何解释，需要大量逆向工程才能弄清，这违背了差分隐私的核心优势——用户应能基于数据收集方公布的可量化风险来决定是否加入；2) 缺乏透明度为 Apple 有意或无意的滥用敞开大门，比如单方面修改单条数据的隐私损失或损失速率、引入新的 BudgetKeyName，就能在无人知情或同意的情况下大幅削弱隐私保证。Apple 闭源、无文档的做法也无济于事。

ChrisCinelli查看英文原文

To me it comes to: 1) "The privacy loss permitted by the system is not explained anywhere and takes significant effort to reverse-engineer. This is contrary to one of the main conceptual advantages of differential privacy – that a user can make an informed choice whether to opt-in to differentially private data collection based on the quantifiable knowledge of risk announced by the data collector." 2) "Furthermore, the lack of transparency on privacy loss opens the door for intentional or un-intentional abuse by Apple itself, e.g., by unilaterally changing either the per-datum privacy loss or the rate of privacy loss in a time period or by introducing additional BudgetKeyName(s), Apple may significantly weaken the privacy guarantees provided without anyone’s knowledge or consent." Apple's "closed source and no documentation everything" does not help.

历次讨论

2017Hacker News 讨论帖180 分 · 39 评
2019Hacker News 讨论帖59 分 · 8 评

HN 二十年，最值得读的论文。

朋友分享的书单

专题阅读路线

本周最多人读

我的书单

必读 30 篇

论文库

这些论文是怎么挑出来的

全量扫一遍

只留论文本身

写导读、译评论

Apple 在 macOS 10.12 中差分隐私实现的隐私损失

导读

HN 评论精选

相关资源

历次讨论

同领域还值得读

如何入侵一台已关机的电脑：在 Intel ME 中运行未签名代码

比特币：一种点对点的电子现金系统（2008）

GPRS 加密算法 GEA-1 的密码分析表明存在故意弱点

Signal 消息协议的形式化安全分析

A2：模拟恶意硬件

打赏支持

关注向阳乔木