Robustness, Detectability, and Data Privacy in AI // Vinu Sankar Sadasivan // #289

Feb 7, 2025

Vinu Sankar Sadasivan, a PhD candidate at the University of Maryland and Student Researcher at Google DeepMind, dives into the crucial themes of AI robustness and security. He discusses the challenges of jailbreaking multimodal models and explores innovative watermarking techniques for identifying AI-generated content. Vinu highlights the complexities of red teaming practices and automated vulnerability exploitation, showcasing the ongoing battle between AI manipulators and defenders. This engaging session sheds light on the future of safe AI applications across various fields.

Ask episode

Chapters

Transcript

Episode notes

Intro

00:00 • 1min

Challenges of Watermarking and Detecting AI-Generated Text

01:21 • 6min

Navigating AI Text Detection and Concealment

06:57 • 26min

The Evolution of Red Teaming in AI: From Manual Prompts to Automated Techniques

33:10 • 5min

Advancements in AI Vulnerability Exploitation

37:54 • 6min

Analyzing Inputs and Outputs in AI Systems

44:04 • 2min

Red Teaming AI: Strategies and Vulnerabilities

45:47 • 7min

Vinu Sankar Sadasivan is a CS PhD ... Currently, I am working as a full-time Student Researcher at Google DeepMind on jailbreaking multimodal AI models. Robustness, Detectability, and Data Privacy in AI // MLOps Podcast #289 with Vinu Sankar Sadasivan, Student Researcher at Google DeepMind. // Abstract Recent rapid advancements in Artificial Intelligence (AI) have made it widely applicable across various domains, from autonomous systems to multimodal content generation. However, these models remain susceptible to significant security and safety vulnerabilities. Such weaknesses can enable attackers to jailbreak systems, allowing them to perform harmful tasks or leak sensitive information. As AI becomes increasingly integrated into critical applications like autonomous robotics and healthcare, the importance of ensuring AI safety is growing. Understanding the vulnerabilities in today’s AI systems is crucial to addressing these concerns. // Bio Vinu Sankar Sadasivan is a final-year Computer Science PhD candidate at The University of Maryland, College Park, advised by Prof. Soheil Feizi. His research focuses on Security and Privacy in AI, with a particular emphasis on AI robustness, detectability, and user privacy. Currently, Vinu is a full-time Student Researcher at Google DeepMind, working on jailbreaking multimodal AI models. Previously, Vinu was a Research Scientist intern at Meta FAIR in Paris, where he worked on AI watermarking. Vinu is a recipient of the 2023 Kulkarni Fellowship and has earned several distinctions, including the prestigious Director’s Silver Medal. He completed a Bachelor’s degree in Computer Science & Engineering at IIT Gandhinagar in 2020. Prior to their PhD, Vinu gained research experience as a Junior Research Fellow in the Data Science Lab at IIT Gandhinagar and through internships at Caltech, Microsoft Research India, and IISc. // MLOps Swag/Merch https://shop.mlops.community/ // Related Links Website: https://vinusankars.github.io/ --------------- ✌️Connect With Us ✌️ ------------- Join our slack community: https://go.mlops.community/slack Follow us on Twitter: @mlopscommunity Sign up for the next meetup: https://go.mlops.community/register Catch all episodes, blogs, newsletters, and more: https://mlops.community/ Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/ Connect with Richard on LinkedIn: https://www.linkedin.com/in/vinusankars/