Vulnerabilities of Machine Learning Infrastructure

As presented at The Standoff online cyber-range and security conference by Sergey Gordeychik.

In this talk we will present results of hands-on vulnerability research of different components of AI infrastructure including NVIDIA DGX GPU servers, ML frameworks such as Pytorch, Keras and Tensorflow, data processing pipelines and specific applications, including Medical Imaging and face recognition powered CCTV. Updated Internet Census toolkit based on the Grinder framework will be introduced.

GradeZero - Expansion

Sooner or later, everyone has a moment when we find ourselves at the end of the road. A path that seemed to us endless and promised at its end shimmering victories. But instead, all our dreams and hopes become empty, dull and meaningless. The hero of "Expansion" decided to manage it in a cardinal way - he flew to Mars. 

NVIDIA DGX machine learning servers vulnerabilities

NVIDIA has published fixes for vulnerabilities in NVIDIA Machine learning servers with CVSS up to 9.8.

NVIDIA DGX-1, DGX-2, and DGX A100 Servers are affected and can be hacked via BMC OOB interfaces. 

codeblue.jp talk

Vulnerabilities of Machine Learning Infrastructure talk to be presented at Code Blue 2020 security conference @Tokyo. 

Non Cyber Release

Grade Zero - Walls of Your Silence 

http://band.link/xQq41

Grade Zero - Стены твоей тишины 

http://band.link/Dybn6

Enjoy

Wind Turbines strikes again

 

Nice to see Nordex devices featured in SCADA StrangeLove "Too Smart Grid in da Cloud" talk back to 2014 available via SatCOM in 2020.

Vulnerabilities in AI Healthcare pipelines

Must see if you use/develop Artificial Intelligence in Healthcare and care about Cybersecurity and Privacy.