BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: Attacks on Tiny Intelligence\n   When: Sunday\, Aug 
 14\, 10:30 - 11:20 PDT\n   Where: Caesars Forum - Summit 220->236 (AI Vill
 age) - [1]Map\n\n   SpeakerBio:Yuvaraj Govindarajulu \n   No BIO availabl
 e\n\n   Description:\n   As of this year\, there are over a 2.5 billion Ed
 ge-enabled IoT devices\n   and close to 1.5 million new AI Edge devices pr
 ojected to be shipped.\n   These devices include smaller compressed versio
 ns of AI models running\n   on them. While in the last years\, we have bee
 n able to improve the\n   performance of the AI models and reduce their me
 mory footprint on\n   these devices\, not much has been spoken about the s
 ecurity threats of\n   the AI models on tiny models.\n\n   First step towa
 rds protecting these AI models from attacks such as\n   Model Theft\, evas
 ion and data poisoning\, would be to study the\n   efficacy of attacks on 
 these Tiny Intelligent systems. Some of them at\n   the lower Hardware and
  software layers could be protected through\n   classical embedded securit
 y\, they alone would not suffice to protect\n   these Tiny Intelligence. M
 any of these tiny devices (microcontrollers)\n   do not come with built-in
  security features because of their price and\n   power requirements. So a
 n understanding of how the core AI algorithm\n   could be attacked and pro
 tected become necessary. In this talk we go\n   about discussing what coul
 d be the possible threats to these devices\n   and provide directions on h
 ow additional AI security measures would\n   save the Tiny intelligence.\n
 \n   '\n\n   1. https://defcon.outel.org/consolidated_page.html#CaesarsSum
 mitBR\n\n\n
DTEND:20220814T182000Z
DTSTART:20220814T173000Z
LOCATION:AIV - Caesars Forum - Summit 220->236 (AI Village)
SUMMARY:Attacks on Tiny Intelligence
END:VEVENT
END:VCALENDAR