Skip to content

Commit ea3f247

Browse files
committed
docs: Update README.md
1 parent 2b3b06c commit ea3f247

File tree

2 files changed

+2
-2
lines changed

2 files changed

+2
-2
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@
1010

1111
# Introduce
1212

13-
Baize is the first machine-based privacy engine in China that runs directly on the browser, blocking tracking scripts and malicious ad scripts. Developed in JavaScript, it can run in Node.js, browser environment.
13+
Baize is the machine learning based privacy engine that runs directly on the browser, blocking tracking scripts and malicious ad scripts. Developed in JavaScript, it can run in Node.js, browser environment.
1414

1515
Traditional filtering is done using filter rules, but these are based on manual updates from open source organizations, public service organizations, or individuals and are labor-intensive to maintain. We propose an automatic and effective machine learning approach based on integration learning, mimicking the heuristic engine of antivirus software. The multidimensional features of scripts are used to learn and create classifiers to block tracking scripts and malicious ad scripts.
1616

README_ZH.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
77
# 介绍
88

9-
白泽是国内首个直接运行在浏览器上且基于机器的隐私保护引擎,能够有效的阻挡跟踪脚本、恶意广告脚本。使用 JavaScript 开发,可以运行在 Node.js、浏览器环境中。
9+
白泽是直接运行在浏览器上且基于机器的隐私保护引擎,能够有效的阻挡跟踪脚本、恶意广告脚本。使用 JavaScript 开发,可以运行在 Node.js、浏览器环境中。
1010

1111
传统的过滤方式是使用过滤规则进行过滤,但这些过滤规则都是基于开源组织、公益组织或个人手动更新的,需要耗费大量的人力进行维护。我们模仿杀毒软件的启发式引擎,基于集成学习,提出了一种自动有效的机器学习方法。通过脚本的多维度特征来学习并创建分类器从而阻止跟踪脚本及恶意广告脚本。
1212

0 commit comments

Comments
 (0)