Machine Learning CTF
Awareness: Demonstrating Capabilities
ML 100: Machine Learning with TensorFlow (65 pts extra)ML 101: Computer Vision (10 pts extra)
ML 102: Breaking a CAPTCHA (10 pts extra)
ML 103: Deblurring Images (40 pts extra)
Technical: Inner Components
ML 104: Analyzing Input Data (20 pts extra)ML 105: Classification (15 pts extra)
ML 106: Data Poisoning (10 pts extra)
Attacks
ML 107: Evasion Attack with SecML (40 pts extra)ML 108: Evasion Attack on MNIST dataset (40 pts extra)
ML 109: Poisoning Labels with SecML (30 pts extra)
ML 110: Poisoning by Gradients (40 pts extra)
ML 111: Poisoning the MNIST datase (40 pts extra)
Large Language Models
ML 120: Bloom LLM (30 pts extra)ML 121: Prompt Engineering Concepts (20 pts extra)
ML 122: Comparing LLMs on Colab (20 pts extra)
ML 130: Prompt Injection (95 pts extra)
Under Development
- The Cleverhans attack library
- Deep Neural Rejection (a defense mechanism)
- Detecting Malware
- Linear and polynomial regression
- Overfitting and underfitting
References
SecML: Secure and Explainable Machine Learning in PythonChatGPT Prompt Engineering for Developers
Prompt Engineering Guide
Google's Generative AI learning path
Archived Scores
Spring 2023