Presented at
DEF CON 31 (2023),
Aug. 11, 2023, 2 p.m.
(240 minutes)
Every technical product is now incorporating machine learning at an explosive rate. But most people, even those with strong technical skills, don't understand how it works, what its capabilities are, and what security risks come with it. In this workshop, we'll make machine learning models using simple Python scripts, train them, and evaluate their value. Projects include computer vision, breaking a CAPTCHA, deblurring images, regression, and classification tasks. We will perform poisoning and evasion attacks on machine learning systems, and implement deep neural rejection to block such attacks.
No experience with programming or machine learning is required, and the only software required is a Web browser. We will use TensorFlow on free Google Colab cloud systems.
All materials and challenges are freely available at samsclass.info, and will remain available after the workshop ends.
Skill Level: Beginner
Prerequisites for students:
- None
Materials or Equipment students will need to bring to participate:
- A computer with a Web browser
Presenters:
-
Irvin Lemus
Irvin Lemus, CISSP is a Cyber Range Engineer at By Light IT Professional Services, training military personnel through international cyber security exercises. Irvin has been in the field since 2006, involved with cybersecurity competitions since 2015 as a trainer, coach, and mentor. He also has taught IT and Cybersecurity courses at Coastline and Cabrillo Colleges. He is the BACCC Cyber Competitions Regional Coordinator, Board member at Pacific Hackers and is a speaker at DEFCON. He describes himself as, "A professional troublemaker who loves hacking all the things."
-
Kaitlyn Handelman
- Offensive Security Engineer at Amazon
Kaitlyn Handelman is an offensive security engineer at Amazon. Her focus is cybersecurity in space. In addition to traditional penetration testing, Kaitlyn works on physical devices and RF signals. In her free time, she enjoys ham radio, astronomy, and her cat, Astrocat.
-
Elizabeth Biddlecome
Elizabeth Biddlecome is a consultant and instructor, delivering technical training and mentorship to students and professionals. She leverages her enthusiasm for architecture, security, and code to design and implement comprehensive information security solutions for business needs. Elizabeth enjoys wielding everything from soldering irons to scripting languages in cybersecurity competitions, hackathons, and CTFs.
-
Sam Bowne
- Founder at Infosec Decoded, Inc
Sam Bowne has been teaching computer networking and security classes at City College San Francisco since 2000, and is the founder of Infosec Decoded, Inc. He has given talks and hands-on trainings at Black Hat USA, RSA, DEF CON, DEF CON China, HOPE, and many other conferences.
Credentials: PhD, CISSP, DEF CON Black Badge Co-Winner
Similar Presentations: