Aggregator
Web Application and API Protection: From SQL Injection to Magecart
聊聊Google的工程实践(二)
聊聊Google的工程实践(二)
聊聊Google的工程实践(二)
开源信息收集周报#56
开源信息收集周报#56
Every Application Should Be Behind a WAF
DDCTF 2020 Writeup
今年改了赛制, 可以两人组队, 我觉得改的还是不错的, 终于不用现场表演学习逆向和 pwn 了, 成功和 Ary 师傅打到了第三 233
对数据安全的一些思考
对数据安全的一些思考
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
WebLogic 反序列化CVE连环三连击
Threat modeling a machine learning system
This post is part of a series about machine learning and artificial intelligence. Click on the blog tag “huskyai” to see all the posts, or visit the machine learning attack series overview section.
In the previous post we walked through the steps required to gather training data, build and test a model to build “Husky AI”.
This post is all about threat modeling the system to identify scenarios for attacks which we will perform in the upcoming posts.
MLOps - Operationalizing the machine learning model
This post is part of a series about machine learning and artificial intelligence.
In the previous post we walked through the steps required to gather training data, build and test a model.
In this post we dive into “Operationalizing” the model. The scenario is the creation of Husky AI and my experiences and learnings from that.
Part 3 - Operationalizing the Husky AI modelThis actually took much longer than planned.
Since I used TensorFlow, I naively thought it would be very straight forward to implement a Golang web server to host the model. Turns out that TensorFlow/Keras is not that as straightforward to integrate with Golang, it requires a lot of extra steps. So, I ended up picking Python for the web server.