BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//bsideslv24//speaker//QZFQ9E
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20230807T000000
TZNAME:PDT
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T020000
RDATE:20241103T020000
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T030000
RDATE:20250309T030000
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Devising and detecting spear phishing using data scraping\, large 
 language models\, and personalized spam filters - Fred Heiding\, Simon Ler
 men
DTSTART;TZID=America/Los_Angeles:20240806T113000
DTEND;TZID=America/Los_Angeles:20240806T121500
DTSTAMP:20260819T084004Z
UID:pretalx-bsideslv24-8WK8P3@pretalx.com
DESCRIPTION:We previously demonstrated how large language models (LLMs) ex
 cel at creating phishing emails (https://www.youtube.com/watch?v=yppjP4_4n
 40). Now\, we continue our research by demonstrating how LLMs can be used 
 to create a self-improving phishing bot that automates all five phases of 
 phishing emails (collecting targets\, collecting information about the tar
 gets\, creating emails\, sending emails\, and validating the results). We 
 evaluate the tool using a factorial approach\, targeting 200 randomly sele
 cted participants recruited for the study. First\, we compare the success 
 rates (measured by pressing a link in an email) of our AI-phishing tool an
 d phishing emails created by human experts. Then\, we show how to use our 
 tool to counter AI-enabled phishing bots by creating personalized spam fil
 ters and a digital footprint cleaner that helps users optimize the informa
 tion they share online. We hypothesize that the emails created by our full
 y automated AI-phishing tool will yield a similar click-through rate as th
 ose created using human experts\, while reducing the cost by up to 99%. We
  further hypothesize that the digital footprint cleaner and personalized s
 pam filters will result in tangible security improvements at a minimal cos
 t.
LOCATION:Siena
URL:https://pretalx.com/bsideslv24/talk/8WK8P3/
END:VEVENT
END:VCALENDAR