AI Training Series: Watermarking and Santization

Discover the art and science of concealing information in plain sight. This training session offers a comprehensive introduction to the fundamental techniques for hiding data within digital images. Participants will learn about various steganographic methods, including least significant bit manipulation and frequency domain techniques, as well as deep learning watermarking strategies used for copyright protection and authentication. Through a combination of practical exercises, you'll gain hands-on experience in embedding and extracting hidden information using modern tools and algorithms. The seminar will also discuss the ethical considerations, legal implications, and best practices for responsible use of these technologies in today's digital landscape.

Preston Robinette is a 5th year PhD student in Computer Science at Vanderbilt University, where she works in Dr. Taylor T. Johnson’s Verification and Validation for Intelligent and Trustworthy Autonomy Laboratory (VeriVITAL). She is interested in research related to generative AI, information hiding, reinforcement learning, machine learning applications, and cybersecurity. Preston is a recipient of the National Defense Science and Engineering Graduate Fellowship Award and the 2023 Vanderbilt University ABS Scholarship Award. She earned a BS in Physics from Presbyterian College and has completed internships at ORNL, NASA, AFRL, NSA, Apple, and Google, where she is currently a Student Research on the Google Gemini team.