BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: On Your Ocean's 11 Team\, I'm the AI Guy (technicall
 y Girl)\n   When: Friday\, Aug 9\, 12:00 - 12:45 PDT\n   Where: LVCC West/
 Floor 1/Hall 1/Track 2 - [1]Map\n\n   Description:\n\n   One of the best p
 arts of DEF CON is the glitz and glam of Vegas\, the\n   gambling capital 
 of the world. Many have explored hacking casinos (on\n   and off stage). U
 nfortunately\, it’s just not like it is portrayed in\n   the Oceans fran
 chise.. in real life there’s much less action\, no\n   George Clooney\, 
 and it’s a lot harder to pull off a successful\n   heist.\n\n   Fortunat
 ely I’m not your typical hacker\, I’m an AI hacker. I use\n   adversar
 ial machine learning techniques to disrupt\, deceive and\n   disclose info
 rmation from Artificial Intelligence systems.\n\n   I chose my target care
 fully: Canberra Casino. It’s the best casino\n   in my city.. It’s als
 o the only casino but that’s not the point.\n   The casino industry is a
 t an interesting inflection point. Many large\n   casinos have already ado
 pted AI for surveillance and gameplay\n   monitoring\, smaller casinos are
  starting to make the transition\, and\n   there’s only a couple of comp
 anies in the world that provide this\n   software. It’s ripe for exploit
 ation.\n\n   In this talk I’m going to show you how I bypassed Casino Ca
 nberra's\n   AI systems - facial recognition\, surveillance systems and ga
 meplay\n   monitoring. AI Security is the new cyber security threat\, and 
 attacks\n   on AI systems could have broad implications including misdiagn
 oses in\n   medical imaging\, navigation errors in autonomous vehicles.. a
 nd\n   successful casino heists.\n\n     1. Standing Committee of the One 
 Hundred Year Study of Artificial\n       Intelligence. Gathering Strength\
 ,Gathering Storms: The One Hundred\n       Year Study on Artificial Intell
 igence (AI100) 2021 Study Panel\n       Report | One Hundred Year Study on
  Artificial Intelligence\n       (AI100). Technical report\, September 202
 1.\n\n     2. Eva A. M. van Dis\, Johan Bollen\, Willem Zuidema\, Robert v
 an\n       Rooij\, and Claudi L. Bockting. ChatGPT: five priorities for\n 
       research. Nature\, 614(7947):224–226\, February 2023. Bandiera\n  
      abtest: a Cg type: Comment Number: 7947 Publisher: Nature\n       Pub
 lishing Group Subject term: Com-puter science\, Research\n       managemen
 t\, Publishing\, Machine learning.\n\n     3. Mingfu Xue\, Chengxiang Yuan
 \, Heyi Wu\, Yushu Zhang\, and Weiqiang\n       Liu. Machine Learn-ing Sec
 urity: Threats\, Countermeasures\, and\n       Evaluations. IEEE Access\, 
 8:74720–74742\, 2020.Conference Name:\n       IEEE Access.\n\n     4. NS
 CAI. The National Security Commission on Artificial\n       Intelligence.\
 n\n     5. Elisa Bertino\, Murat Kantarcioglu\, Cuneyt Gurcan Akcora\, Sag
 ar\n       Samtani\, Sudip Mittal\, and Maanak Gupta. AI for Security and\
 n       Security for AI. In Proceedings of the Eleventh ACM Confer-ence on
 \n       Data and Application Security and Privacy\, CODASPY ’21\, pages
 \n       333–334\, New York\, NY\, USA\, April 2021. Association for\n  
      Computing Machinery.\n\n     6. Battista Biggio and Fabio Roli. Wild 
 patterns: Ten years after\n       the rise of adversarial machine learning
 . Pattern Recognition\,\n       84:317–331\, December 2018.\n\n     7. I
 an Goodfellow\, Jonathon Shlens\, and Christian Szegedy.\n       Explainin
 g and Harnessing Adversarial Examples. In International\n       Conference
  on Learning Representations\, 2015.\n\n     8. Christian Szegedy\, Wojcie
 ch Zaremba\, Ilya Sutskever\, Joan Bruna\,\n       Dumitru Erhan\, Ian Goo
 dfellow\, and Rob Fergus. Intriguing\n       properties of neural networks
 \, February 2014. arXiv:1312.6199\n       [cs].\n\n     9. Mahmood Sharif\
 , Sruti Bhagavatula\, Lujo Bauer\, and Michael K.\n       Reiter. Accessor
 ize to a Crime: Real and Stealthy Attacks on\n       State-of-the-Art Face
  Recognition. In Proceedings of the 2016 ACM\n       SIGSAC Conference on 
 Computer and Communications Security\, CCS\n       ’16\, pages 1528–15
 40\, New York\, NY\, USA\, October 2016.\n       Association for Computing
  Machinery.\n\n     10. Tom Brown\, Dandelion Mane\, Aurko Roy\, Martin Ab
 adi\, and Justin\n       Gilmer. Adversarial Patch. 2017.\n\n     11. US M
 arines Defeat DARPA Robot by Hiding Under a Cardboard Box |\n       Extrem
 etech.\n\n     12. Walter David\, Paolo Pappalepore\, Alexandra Stefanova\
 , and\n       Brindusa Andreea Sarbu. AI-Powered Lethal Autonomous Weapon\
 n       Systems in Defence Transformation. Impact and Chal-lenges. In Jan\
 n       Mazal\, Adriano Fagiolini\, and Petr Vasik\, editors\, Modelling a
 nd\n       Simulation for Autonomous Systems\, Lecture Notes in Computer\n
        Science\, pages 337–350\, Cham\, 2020. Springer International\n  
      Publishing.\n\n     13. C Wise and J Plested. Developing Imperceptibl
 e Adversarial\n       Patches to Camouflage Military Assets From Computer 
 Vision Enabled\n       Technologies\, May 2022. arXiv:2202.08892 cs..\n\n 
     14. Anish Athalye\, Nicholas Carlini\, and David Wagner. Obfuscated\n 
       Gradients Give a False Sense of Security: Circumventing Defenses\n  
      to Adversarial Examples. In Proceedings of the 35th International\n  
      Conference on Machine Learning\, pages 274–283. PMLR\, July 2018.\n
        ISSN: 2640-3498.\n\n     15. Kevin Eykholt\, Ivan Evtimov\, Earlenc
 e Fernandes\, Bo Li\, Amir\n       Rahmati\, Chaowei Xiao\, Atul Prakash\,
  Tadayoshi Kohno\, and Dawn\n       Song. Robust Physical-World Attacks on
  Deep Learning Visual\n       Classification. In 2018 IEEE/CVF Conference 
 on Computer Vision and\n       Pattern Recognition\, pages 1625–1634\, S
 alt Lake City\, UT\, USA\,\n       June 2018. IEEE.\n\n     16. Ram Shanka
 r Siva Kumar\, Magnus Nystr ̈om\, John Lambert\, Andrew\n       Marshall\
 , Mario Goertzel\, Andi Comissoneru\, Matt Swann\, and Sharon\n       Xia.
  Adversarial Machine Learning-Industry Perspectives. In 2020\n       IEEE 
 Security and Privacy Workshops (SPW)\, pages 69–75\, May\n       2020.\n
 \n   SpeakerBio:  Harriet Farlow\, CEO at Mileva Security Labs\n\n   Harri
 et Farlow is the CEO of AI Security company Mileva Security Labs\,\n   a P
 hD Candidate in Machine Learning Security\, and creative mind behind\n   t
 he YouTube channel HarrietHacks. She missed the boat on computer\n   hacki
 ng so now she hacks AI and Machine Learning models instead. Her\n   career
  has spanned consulting\, academia\, a start-up and Government\,\n   but d
 on’t judge her for that one. She also has a Bachelor in Physics\n   and 
 a Master in Cyber Security. She calls Australia home but has lived\n   in 
 the UK and the US. Her ultimate hack was in founding her own AI\n   Securi
 ty company but if Skynet takes over she will deny everything and\n   prete
 nd the AI stood for Artificial Insemination\, like her Mum thinks\n   it d
 oes. (Sorry Mum but I’m not really a Medical Doctor).\n\n   '\n\n   1. #
 LVCCW_Level1_Hall1\n\n\n
DTEND:20240809T194500Z
DTSTART:20240809T190000Z
LOCATION:DC - LVCC West/Floor 1/Hall 1/Track 2
SUMMARY:On Your Ocean's 11 Team\, I'm the AI Guy (technically Girl)
END:VEVENT
END:VCALENDAR