GradeZero - World of Broken Stuff

 

New GradeZero single is on the air. 

World of Broken Stuff

Мир поломанных вещей

NVIDIA DGX A100 Security Update

The DGX A100 System Firmware Update container version 20.11.3 for Ubuntu with BMC version 00.13.04 fixes vulnerabilities described in NVIDIA Security Bulletin 5010 such as CVE‑2020‑11487.

More details can be found in recent AISec talks and releases. 

Enjoy

GradeZero - 1:30 AM

At half past one, time freezes. There is no night, no day. There is no sun and moon. Only you and the emptiness into which yesterday's thoughts leave and from which the verses that create Tomorrow comes.

New musical release by GradeZero.band

Russian

English

Vulnerabilities of Machine Learning Infrastructure (Slides/Video)

Vulnerabilities of Machine Learning Infrastructure talk as presented at CodeBlue 2020 Japan and Standoff365 by Sergey Gordeychik.

The boom of AI brought to the market a set of impressive solutions both on the hardware and software side. On the other hand, massive implementation of AI in various areas brings about problems, and security is one of the greatest concerns.

Cyber Resilience of Railway Signaling Systems - Russian book

Updated Russian version of the Railway Cybersecurity hardcopy book by Sergey Gordeichik was published last week. 

Кибербезопасность микропроцессорных систем управления на железнодорожном транспорте 

Гордейчик Сергей Владимирович

GradeZero - A Chance

In the hustle and bustle, it is very easy to walk past the crossroads of Fortune, points where we can change our destination and take a new path. Often her signs interfere with us, annoy us and we try not to notice them, fearing to fall out of rhythm, even if the usual rut does not bring anything more than a kaleidoscope of glasses.

Listen carefully, watch out! Fate always gives a new chance, don't miss it!

Russian

English 

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.