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: Virtual\n\n   Description:\n\n   The AutoDr
 iving CTF contest focuses on the emerging security\n   challenges in auton
 omous driving systems. Various levels of\n   self-driving functionalities\
 , such as AI-powered perception\, sensor\n   fusion and route planning\, a
 re entering the product portfolio of\n   automobile companies. From the se
 curity perspective\, these AI-powered\n   components not only contain comm
 on security problems such as memory\n   safety bugs\, but also introduce n
 ew threats such as physical\n   adversarial attacks and sensor manipulatio
 ns. Two popular examples of\n   physical adversarial attacks are camouflag
 e stickers that interfere\n   with vehicle detection systems\, and road gr
 affitis that disturb lane\n   keeping systems. The AI-powered navigation a
 nd control relies on the\n   fusion of multiple sensor inputs\, and many o
 f the sensor inputs can be\n   manipulated by malicious attackers. These m
 anipulations combined with\n   logical bugs in autonomous driving systems 
 pose severe threats to road\n   safety.\n\n   We design autonomous driving
  CTF (AutoDriving CTF) contests around the\n   security challenges specifi
 c to these self-driving functions and\n   components.\n\n   The goals of t
 he AutoDriving CTF are the followings:\n\n     * Demonstrate security impl
 ications of autonomous driving system\n       design decisions through han
 ds-on challenges\, increase the\n       awareness of potential risks in se
 curity professionals\, and\n       encourage them to propose defense solut
 ions and tools to detect\n       such risks.\n\n     * Provide CTF challen
 ges that allow players to learn attack and\n       defense practices relat
 ed to autonomous driving in a\n       well-controlled\, repeatable\, and v
 isible environment.\n\n     * Build a set of vulnerable autonomous driving
  components that can\n       be used for security research and defense eva
 luation.\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 driving components in simulated or real\
 n   environments\, and a frontend that interacts with the players. This\n 
   year's contest will follow the style of last year and includes the\n   f
 ollowing types of challenges:\n\n     * “attack”: such as constructing
  adversarial patches and\n       spoofing fake sensor inputs\,\n\n     * �
 ��forensics”: such as investigating a security incident related\n       
 to autonomous driving\,\n\n     * “detection”: such as detecting spoof
 ed sensor inputs and fake\n       obstacles\,\n\n     * “crashme on road
 !”: such as creating dangerous traffic\n       scenarios to expose logic
 al errors in autonomous driving systems.\n\n     * “smart planner”: su
 ch as creating intelligent path planners\n       for dangerous tasks that 
 are difficult for human drivers\n\n   Most of these challenges will be dev
 eloped using game-engine based\n   autonomous driving simulators\, such as
  CARLA and SVL. The following\n   link contains some challenge videos\, su
 mmaries from AutoDriving CTF at\n   DEF CON 29 and DEF CON 30\n   https://
 drive.google.com/drive/folders/1JSVarIaQBmseLC9XqkfrxnRQto4WM225?usp=shari
 ng\n   https://www.youtube.com/channel/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 driv
 ing logs such as Jaywalk and double\n   parked vehicles. New difficulty le
 vels will be added to challenges in\n   such scenarios by integrating real
  downstream AI modules such as\n   object tracking from open-source autono
 mous driving software like\n   Apollo\, Autoware and OpenPilot.\n\n   In o
 rder to enable the audience to experience 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 can 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_ntX5eFu82U9Ob
 iEYB?usp=sharing\n\n\n\n   For players\n   ===========\n\n     * \n\n     
   What do players need to do to participate AutoDriving CTF? Most of\n    
    the challenges do not require domain knowledge of autonomous\n       dr
 iving software or adversarial machine learning\, although\n       knowledg
 e of those helps. For example\, the players can generate\n       images th
 e way they like (e.g.\, drawing\, photoshopping) to fool\n       the AI-co
 mponents or write a short python script to control the\n       vehicle. So
 me challenges\, such as incident forensics likely would\n       require pl
 ayers to learn domain knowledge such as sensor\n       information format 
 and how fusion works.\n\n     * \n\n       What do we expect players to le
 arn through the CTF event? Players\n       can (1) gain a deep understandi
 ng of real-world autonomous driving\n       systems' design\, implementati
 on\, and their corresponding security\n       properties and characteristi
 cs\; and (2) learn the attack and\n       defense practices related to aut
 onomous driving in a\n       well-controlled\, repeatable\, visible\, and 
 engaging environment.\n\n   '\n\n
DTEND:20240810T005900Z
DTSTART:20240809T170000Z
LOCATION:CON - Virtual
SUMMARY:[CANCELED] AutoDriving CTF
END:VEVENT
END:VCALENDAR