BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.balccon.org//balccon2k26-2026//talk//AP9VB7
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-balccon2k26-2026-AP9VB7@cfp.balccon.org
DTSTART;TZID=CET:20260918T150500
DTEND;TZID=CET:20260918T155000
DESCRIPTION:With the use of AI agents catching wind across the offensive se
 curity space\, from social engineering to vulnerability research\, it was 
 inevitable that malware would follow suit. While most discussions focus on
  targeting AI\, using it to generate malicious payloads at a malware’s r
 untime\, or “vibe coding” it\, we went a step further: we built a syst
 em where AI is the sole participant in the malware creation process itself
 .\nWe will begin by talking about how we got to this point\, what sparked 
 the idea\, and jump into comparing different models – showing which gave
  the best code\, which was most evasive\, which prompts worked the best\, 
 and what we used in the agent.\nWe will then dig into the generation proce
 ss itself – we will show the challenges with earlier approaches\, how we
  solved them\, how to build the workflow to maximize the malware’s capab
 ility and randomization\, how it managed to break signatures\, and how to 
 generate millions of samples.\nWe will finish by showing how attackers are
  using similar methods\, look at real examples in the wild\, and discuss h
 ow to use these techniques for ourselves\, both as attackers and defenders
 .
DTSTAMP:20260901T064409Z
LOCATION:Tesla
SUMMARY:The Agents of Chaos: AI Driven Malware Generation - Arad Donenfeld
URL:https://cfp.balccon.org/balccon2k26-2026/talk/AP9VB7/
END:VEVENT
END:VCALENDAR