BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: SDLC Nightmares - Defeating Secure Code Review GPT\n
    Hallucinations\n   When: Friday\, Aug 9\, 13:15 - 13:45 PDT\n   Where: 
 LVCC West/Floor 2/W228-W230/W228-W230-ASV Main Stage - [1]Map\n\n   Descri
 ption:\n\n   In this talk\, we will discuss the strengths and limitations 
 of LLMs\n   for code analysis tasks like code search and code clone detect
 ion. We\n   will show when the LLMs make mistakes and what kinds of mistak
 es they\n   make. For example\, we observe that the performance of popular
  LLMs\n   heavily relies on the well-defined variable and function names\,
 \n   therefore\, they will make mistakes when some misleading variable nam
 e\n   is given. Anyone interested in exploring the intersection of AI and\
 n   code security analysis can attend this talk.\n\n   Speakers:Wang Zhilo
 ng\,Xinzhi Luo\n\n   SpeakerBio:  Wang Zhilong\n\n   Now security engineer
  in industry.\n\n   Ph.D. degree obtained from Penn State University in 20
 23.\n\n   Master degree obtained from Nanjing University in 2019.\n\n   Sp
 eakerBio:  Xinzhi Luo\n\n   Xinzhi (April) Luo is a Carnegie Mellon Univer
 sity graduate with over\n   three years of experience in information secur
 ity. She combines\n   technical expertise with a passion for sci-fi\, ofte
 n writing original\n   stories. She is dedicated to innovative cybersecuri
 ty solutions.\n\n   '\n\n   1. #LVCCW_Level2_North\n\n\n
DTEND:20240809T204500Z
DTSTART:20240809T201500Z
LOCATION:APV - LVCC West/Floor 2/W228-W230/W228-W230-ASV Main Stage
SUMMARY:SDLC Nightmares - Defeating Secure Code Review GPT Hallucinations
END:VEVENT
END:VCALENDAR