安全与密码学2016cs.cmu.edu
对最先进人脸识别系统的真实且隐蔽攻击
Real and Stealthy Attacks on State-Of-the-Art Face Recognition
进阶 · 约 45 分钟读完前置知识:机器学习基础、人脸识别原理、对抗样本概念
导读
这篇 CMU 的论文(CCS 2016)研究如何对人脸识别系统发起真实且隐蔽的对抗攻击:通过在眼镜框上打印特定扰动的图案,攻击者可以欺骗最先进的人脸识别算法,让系统把攻击者误认成目标人物,甚至可以用来隐藏真实人脸。攻击方式物理可行且对人眼相对不显眼。
HN 关注点:人脸识别正被广泛部署于安防和身份验证,这种低成本、可物理实施的欺骗攻击直接威胁其可靠性,因此引发 HN 读者对算法脆弱性和防御手段的讨论。
HN 评论精选
这几条评论里:支持 1 质疑 1 补充 1 亲历 1
质疑认为攻击暴露了算法的根本缺陷,提出分部件识别和噪声过滤等防御思路
人类能轻易识破这种伪装,说明识别算法存在巨大缺陷。这类攻击可能终将被某次突破彻底解决。人类不会因为图像一小部分被噪声覆盖而上当,把人脸各部分分开识别可能有助防御(也能检测出把不同人的眼睛和嘴巴拼接的合成图像)。另外人类一眼就能看出那些眼镜是噪声,或许在人脸识别前应先加一个去除明显噪声的过滤器。
unabridged查看英文原文
The fact humans can easily see through the disguise means there are huge glaring faults in the recognition algorithm. These types of attacks will probably be wiped away one day with a single breakthrough. You can't fool a human by covering up a small percentage of something with noise. Humans can recognize parts of a face pretty well, classifying smaller parts of an image separately may help defend against this (and also be able to detect composite images, for example where eyes and mouth of different people are combined). Also humans instantly detect that those glasses are noise, there probably needs to be a filter that removes obvious noise before the face recognition begins.
亲历亲历分享:面具/伪装攻击早已存在,厂商曾尝试用红外检测来应对
我们做 Kinect 人脸识别时,我常路过 QA 区,渐渐习惯了看到理查德·尼克松、毛泽东、玛丽莲·梦露等人的面具在测试 Kinect 软件栈,起初相当吓人。我记得下一代摄像头改用红外分析来检测面具,不知道效果如何。
kabdib查看英文原文
When we were doing face recognition on Kinect, I'd pass by the Q/A areas and eventually got used to seeing Richard Nixon, Mao Tse-tung, Marilyn Monroe and others dancing around, exercising the Kinect software stack. The masks were pretty startling at first. I think that the next version of the camera did analysis in IR to try to detect masks, I don't know how effective it was.
补充提出关键问题:对抗样本能否通过加入训练数据来修补
好奇一点:既然被测试的人脸识别算法是用机器学习训练的,如果把戴这种眼镜的样本加入训练集,能否得到不再被骗的版本?还是说这是 ML 算法天生防不住的攻击方式?换句话说,这个漏洞能被修补吗?
savanaly查看英文原文
I'm curious, since the facial recognition algorithms they are testing are created with ML, would adding the instances of someone wearing these glasses to the training set result in a version that wouldn't be fooled? Or is the method something the ML algorithms are inherently weak against? Is this an exploit that could be patched, in other words?
支持总结论文核心攻击手法,认为其价值在于攻击的实用性
tl;dr:在眼镜框上印上目标人物图像的扰动版本,就能骗过人脸识别算法,让它把你的脸认成别人(还有更诡异的用法:用类似方法隐藏人脸)。这很酷——算法被骗不稀奇,但能找到如此实用的攻击方式相当厉害。至少现在电脑会觉得我长得像乔治·克鲁尼了,虽然这在酒吧搭讪时没用。
lifeisstillgood查看英文原文
tl;dr Using spectacle frames with the other persons image "perturbed" onto that frame, facial recognition algorithms can be fooled into thinking your face is someone else's. (There is a weirder ability to hide a human face using similar approach.) This is surprisingly cool - the fact that the algorithm can be fooled is not amazing, but that they could find a fairly practical attack is quite impressive. And at least now a computer can think I look like George Clooney, even if it won't work in a singles bar.
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2016Hacker News 讨论帖159 分 · 34 评
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
How to hack a turned-off computer, or running unsigned code in Intel ME
这篇 Black Hat 2017 白皮书讨论 Intel Management Engine(ME)的安全问题:如何在 ME 中运行未签名代码,以及攻破处于关机状态的电脑的相关…
安全与密码学2017 · 543 分 · 107 评专业 · 约 40 分钟编辑精选比特币:一种点对点的电子现金系统(2008)
Bitcoin: A Peer-to-Peer Electronic Cash System (2008)
中本聪 2008 年发表的比特币白皮书,提出了无需可信第三方的点对点电子现金系统。
安全与密码学2017 · 536 分 · 394 评入门 · 约 45 分钟编辑精选GPRS 加密算法 GEA-1 的密码分析表明存在故意弱点
Cryptanalysis of GPRS Encryption Algorithms GEA-1 suggest intentional weakness
首次公开了对 GPRS 加密算法 GEA-1 和 GEA-2 的密码分析攻击。
安全与密码学2021 · 487 分 · 107 评专业 · 约 90 分钟编辑精选Signal 消息协议的形式化安全分析
A Formal Security Analysis of the Signal Messaging Protocol
用形式化方法分析 Signal 消息协议(TextSecure)的安全性:作者在多阶段密钥交换模型下,借助自动化证明工具对协议的密钥协商与 Double Ratchet 密钥更新…
安全与密码学2016 · 353 分 · 230 评专业 · 约 120 分钟编辑精选A2:模拟恶意硬件
A2: Analog Malicious Hardware
论文研究如何在芯片设计阶段植入模拟电路形式的恶意硬件后门,使其难以被常规检测发现。
安全与密码学2016 · 315 分 · 94 评专业 · 约 75 分钟编辑精选