AI Threat Management Workshop

Description

As seasoned cybersecurity educators, mastering the art of AI threat management is essential. This workshop is designed to equip professionals with the knowledge and skills necessary to leverage data science and AI effectively in combating cyber threats. Participants will delve into the transformative potential of AI applications, learning how to harness human intelligence alongside AI technologies to bolster organizational defenses and improve information systems management.

Through a blend of engaging lectures, team activities, lab exercises, and practical examples, attendees will gain invaluable insights into AI methodologies tailored for threat detection, vulnerability assessment, penetration testing, threat hunting, and intelligence gathering. The workshop goes beyond technical aspects, covering essential topics such as AI ethics, governance, risk management, and compliance. Participants will explore the intricacies of building secure AI environments and utilizing AI to assist organizations in performing Privacy Impact Assessments. By the end of the workshop, professionals will emerge equipped with a comprehensive understanding of AI's role in threat management.

  

Scoreboard · Submit Flags

Presentation: Risks of AI    PDF · KEY · PPT

Presentation: AI Workshop Summary    PDF · KEY · PPT

Whole Course with Lectures

Understanding Prompts

ML 130: Prompt Injection (25 pts + 60 extra)
ML 131: Generating Python Code with Bard (40 pts extra)
Violent Python Challenges (extra)

Google Learning

GL_Badges: Google Learning (30 pts + 60 or more extra)

Security Risks

ML 150: OWASP Machine Learning Security Top Ten (15 pts)
ML 151: OWASP Top 10 for LLM Applications (15 pts)
ML 152: Microsoft Copilot Security (15 pts)

Awareness: Demonstrating Capabilities

ML 100: Machine Learning with TensorFlow (20 pts + 45 extra)
ML 101: Computer Vision (10 pts)
ML 102: Breaking a CAPTCHA (10 pts)
ML 103: Deblurring Images (10 pts + 30 extra)

Technical: Inner Components

ML 104: Analyzing Input Data (20 pts)
ML 105: Classification (15 pts + 10 extra)
ML 106: Data Poisoning (10 pts)
ML 112: Support Vector Machines (40 pts extra)
ML 113: Decision Trees (15 pts extra)
ML 114: Ensemble Learning and Random Forests (15 pts extra)
ML 115: Dimensionality Reduction (20 pts extra)
ML 116: k-Means Clustering (30 pts extra)

Attacks

ML 107: Evasion Attack with SecML (15 pts + 25 extra)
ML 108: Evasion Attack on MNIST dataset (20 pts + 20 extra)
ML 109: Poisoning Labels with SecML (20 pts + 10 extra)
ML 110: Poisoning by Gradients (15 pts + 15 extra)
ML 111: Poisoning the MNIST dataset (20 pts + 20 extra)

Defenses

ML 140: Deep Neural Rejection (45 pts extra)

Large Language Models

ML 120: Bloom LLM (15 pts + 15 extra)
ML 121: Prompt Engineering Concepts (20 pts)
ML 122: Comparing LLMs on Colab (10 pts + 10 extra)
ML 123: Running Llama 3 Locally (15 pts extra)
ML 124: Evaluating an LLM with Trulens (15 pts extra)
ML 126: Building RAGs (15 pts extra)
ML 127: Encoding Text with BERT (10 pts extra)
ML 128: Using AnythingLLM to Embed Custom Data (10 pts extra)

ML 125: Jupyter Notebook on a Mac M1 (10 pts extra)

ML 160: GitHub Copilot (15 pts extra)

  

References

SecML: Secure and Explainable Machine Learning in Python
ChatGPT Prompt Engineering for Developers
Prompt Engineering Guide
Google's Generative AI learning path
A jargon-free explanation of how AI large language models work
A friendly guide to local AI image gen with Stable Diffusion and Automatic1111

Archives

Spring 2023 Scores
July 9, 2023 Scores
CCSF CyberCamp July 23, 2023 Scores
CCSF Adv. CyberCamp July, 2023 Scores
Videos from TX State Working Connections Summer 2023
Final Scores from DEF CON 31
Scores from HackTheBay, Summer 2024

Updated: 6-25-24