BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: [CANCELED] AutoDriving CTF\n   When: Friday\, Aug 9\
 , 10:00 - 17:59 PDT\n   Where: LVCC West/Floor 1/Hall 4/HW4-01-05-B - [1]M
 ap\n\n   Description:\n\n   The AutoDriving CTF contest focuses on the eme
 rging security\n   challenges in autonomous driving systems. Various level
 s of\n   self-driving functionalities\, such as AI-powered perception\, se
 nsor\n   fusion and route planning\, are entering the product portfolio of
 \n   automobile companies. From the security perspective\, these AI-powere
 d\n   components not only contain common security problems such as memory\
 n   safety bugs\, but also introduce new threats such as physical\n   adve
 rsarial attacks and sensor manipulations. Two popular examples of\n   phys
 ical adversarial attacks are camouflage stickers that interfere\n   with v
 ehicle detection systems\, and road graffitis that disturb lane\n   keepin
 g systems. The AI-powered navigation and control relies on the\n   fusion 
 of multiple sensor inputs\, and many of the sensor inputs can be\n   manip
 ulated by malicious attackers. These manipulations combined with\n   logic
 al bugs in autonomous driving systems pose severe threats to road\n   safe
 ty.\n\n   We design autonomous driving CTF (AutoDriving CTF) contests arou
 nd the\n   security challenges specific to these self-driving functions an
 d\n   components.\n\n   The goals of the AutoDriving CTF are the following
 s:\n\n     * Demonstrate security implications of autonomous driving syste
 m\n       design decisions through hands-on challenges\, increase the\n   
     awareness of potential risks in security professionals\, and\n       e
 ncourage them to propose defense solutions and tools to detect\n       suc
 h risks.\n\n     * Provide CTF challenges that allow players to learn atta
 ck and\n       defense practices related to autonomous driving in a\n     
   well-controlled\, repeatable\, and visible environment.\n\n     * Build 
 a set of vulnerable autonomous driving components that can\n       be used
  for security research and defense evaluation.\n\n   The contest is based 
 on a Jeopardy style of CTF game with a set of\n   independent challenges. 
 A typical contest challenge includes a backend\n   that runs autonomous dr
 iving components in simulated or real\n   environments\, and a frontend th
 at interacts with the players. This\n   year's contest will follow the sty
 le of last year and includes the\n   following types of challenges:\n\n   
   * “attack”: such as constructing adversarial patches and\n       spo
 ofing fake sensor inputs\,\n\n     * “forensics”: such as investigatin
 g a security incident related\n       to autonomous driving\,\n\n     * �
 �detection”: such as detecting spoofed sensor inputs and fake\n       ob
 stacles\,\n\n     * “crashme on road!”: such as creating dangerous tra
 ffic\n       scenarios to expose logical errors in autonomous driving syst
 ems.\n\n     * “smart planner”: such as creating intelligent path plan
 ners\n       for dangerous tasks that are difficult for human drivers\n\n 
   Most of these challenges will be developed using game-engine based\n   a
 utonomous driving simulators\, such as CARLA and SVL. The following\n   li
 nk contains some challenge videos\, summaries from AutoDriving CTF at\n   
 DEF CON 29 and DEF CON 30\n   https://drive.google.com/drive/folders/1JSVa
 rIaQBmseLC9XqkfrxnRQto4WM225?usp=sharing\n   https://www.youtube.com/chann
 el/UCPPsKbVpxwk-464KIzr8xKw\n\n\n\n   What's new in 2024\n   =============
 =====\n\n   This year\, we will unlock new traffic conflict scenarios that
  are\n   observed from real-world driving logs such as Jaywalk and double\
 n   parked vehicles. New difficulty levels will be added to challenges in\
 n   such scenarios by integrating real downstream AI modules such as\n   o
 bject tracking from open-source autonomous driving software like\n   Apoll
 o\, Autoware and OpenPilot.\n\n   In order to enable the audience to exper
 ience the challenges more\n   directly\, we plan to set up a vehicle wheel
  controller on site and\n   provide a driving game this year. Audiences ca
 n drive themselves to\n   compete with the self-driving vehicle in some of
  the challenges.\n   Driving game demo:\n   https://drive.google.com/drive
 /folders/1LIzJJ1I3Eqj_e0_ntX5eFu82U9ObiEYB?usp=sharing\n\n\n\n   For playe
 rs\n   ===========\n\n     * \n\n       What do players need to do to part
 icipate AutoDriving CTF? Most of\n       the challenges do not require dom
 ain knowledge of autonomous\n       driving software or adversarial machin
 e learning\, although\n       knowledge of those helps. For example\, the 
 players can generate\n       images the way they like (e.g.\, drawing\, ph
 otoshopping) to fool\n       the AI-components or write a short python scr
 ipt to control the\n       vehicle. Some challenges\, such as incident for
 ensics likely would\n       require players to learn domain knowledge such
  as sensor\n       information format and how fusion works.\n\n     * \n\n
        What do we expect players to learn through the CTF event? Players\n
        can (1) gain a deep understanding of real-world autonomous driving\
 n       systems' design\, implementation\, and their corresponding securit
 y\n       properties and characteristics\; and (2) learn the attack and\n 
       defense practices related to autonomous driving in a\n       well-co
 ntrolled\, repeatable\, visible\, and engaging environment.\n\n   '\n\n   
 1. #LVCCW_Level1_Hall4\n\n\n
DTEND:20240810T005900Z
DTSTART:20240809T170000Z
LOCATION:CON - LVCC West/Floor 1/Hall 4/HW4-01-05-B
SUMMARY:[CANCELED] AutoDriving CTF
END:VEVENT
END:VCALENDAR