Aggregator

一共 6 题 WEB, 我一个人拿了 4 个一血, 还有一题全场 0 解. 然而没有 pwn 爷爷依旧被吊打, 而且题目质量是真的差, 明年再打国赛我是傻逼.

This post is part of a series about machine learning and artificial intelligence. Click on the blog tag “huskyai” to see related posts.

• Overview: How Husky AI was built, threat modeled and operationalized
• Attacks: The attacks I want to investigate, learn about, and try out
• Mitigations: Ways to prevent and detect the backdooring threat

During threat modeling we identified that an adversary might tamper with model files. From a technical point of view this means an adversary gained access to the model file used in production and is able overwrite it.

This post is part of a series about machine learning and artificial intelligence. Click on the blog tag “huskyai” to see related posts.

• Overview: How Husky AI was built, threat modeled and operationalized
• Attacks: The attacks I want to investigate, learn about, and try out

The previous post covered some neat smart fuzzing techniques to improve generation of fake husky images.

The goal of this post is to take an existing image of the plush bunny below, modify it and have the model identify it as a husky.

Data privacy and security experts tell us that applying the “need to know” principle enhances privacy and security, because it reduces the amount of information potentially disclosed to a service provider — or to other parties — to the minimum the service provider requires to perform a service.  This principle is at the heart of […]

The post Maximizing Qname Minimization: A New Chapter in DNS Protocol Evolution appeared first on Verisign Blog.