AI Red-Teaming and Security Masterclass

Pliny the Prompter: The most renowned AI Jailbreaker, who has successfully jailbroken every major AI model—including OpenAI's o1, which hasn't even been made public! Pliny also jailbroke an AI agent to autonomously sign into Gmail, code ransomware, compress it into a zip file, write a phishing email, attach the payload, and successfully deliver it to a target

Johann Rehberger: Led the creation of a Red Team in Microsoft Azure as a Principal Security Engineering Manager and built Uber's Red Team. Johann discovered attack vectors like ASCII Smuggling and AI-powered C2 (Command and Control) attacks. He has also found Bug Bounties in OpenAI's ChatGPT, Microsoft Copilot, GitHub Copilot Chat, Anthropic Claude, and Google Bard/Gemini. Johann will be sharing unreleased research that he hasn't yet published on his blog, embracethered.com.

Joseph Thacker: Principal AI Engineer at AppOmni, leading AI research on agentic functionality and retrieval systems. A security researcher specializing in application security and AI, Joseph has submitted over 1,000 vulnerabilities across HackerOne and Bugcrowd. He hacked into Google Bard at their LLM Bug Bounty event and took 1st place in the competition.

Akshat Parikh: Former AI security researcher at a startup backed by OpenAI and DeepMind researchers. Ranked Top 21 in JP Morgan's Bug Bounty Hall of Fame and Top 250 in Google's Bug Bounty Hall of Fame—all by the age of 16.

Richard Lundeen: Principal Software Engineering Lead for Microsoft's AI Red Team and maintainer of Microsoft PyRit. He leads an interdisciplinary team of red teamers, ML researchers, and developers focused on securing AI systems.

Sandy Dunn: A seasoned CISO with 20+ years of experience in healthcare. Project lead for the OWASP Top 10 Risks for LLM Applications Cybersecurity and Governance

Jason Haddix - Bug bounty hunter with over 20-years of experience in cybersecurity as the CISO of Ubisoft, Head of Trust/Security/Operations at Bugcrowd, Director of Penetration Testing at HP, and Lead Penetration Tester at Redspin.

Donato Capitella - A researcher with over 12 years of experience in offensive security and security assurance, has gained a following for his AI security work. Alongside his years of research and blogs on WithSecure, he has taught over 300k people about building and breaking AI systems on his YouTube channel (@donatocapitella).

Valen Tagliabue - An AI researcher, data analyst, and prompt engineer specializing in NLP and cognitive science. His expertise includes LLM evaluation, safety, and alignment, with a strong focus on human-AI collaboration. He was part of the winning team in HackAPrompt2023, an AI safety competition backed by industry leaders like Hugging Face, Scale AI, and OpenAI.

Leonard Tang - Founder and CEO of Haize Labs, an AI safety and evaluation startup based in New York City. Leonard holds Math and CS Bachelor's and Master's degrees from Harvard University and left his Stanford University CS PhD program to start Haize. His team is building next-generation tools for evaluating, red-teaming, monitoring, guardrailing, and robustifying AI systems. Haize Labs' technology is already being used by OpenAI, Anthropic, AI21 Labs, and other leading companies. He was also just awarded Forbes 30 under 30!

David Williams-King - As a co-founder of Elpha Secure and a research scientist at MILA, David Williams-King seamlessly bridges the gap between AI Security and pure cybersecurity. He has researched under the Turing Prize winning Joshua Bengio on his Safe AI For Humanity team.