Noam Schwartz
Co-founder & CEO
Alice
Noam Schwartz is the Co-Founder and CEO of Alice- a trust, safety, and security company built for the AI era, safeguarding communicative technologies across UGC and generative AI. With deep expertise in AI, security, and data science, he previously founded Tapdog, later acquired by SimilarWeb (NYSE: SMWB). Alice is a trusted ally to major technology firms and Fortune 500 brands that develop and operate user-generated and GenAI products. The company has empowered its clients to take proactive steps against a spectrum of internet threats, ensuring the protection of billions of users
Command Desk
Command Desk
What AI Red Teaming Looks Like Outside the Lab
How AI red teaming actually works in enterprise environments — and how it differs from academic or benchmark-based testing.
It demonstrates expertise and realism, without requiring technical fluency.
Attendees will learn:
- What red teaming means beyond prompt injection demos
- The limitations of pre-deployment testing
- Why do misuse tactics/scenarios evolve faster than models
- How leading teams structure continuous adversarial testing
- Based loosely on the Alice Red Teaming framework (from the “Mastering AI red teaming” report, and all other reports as well)
It demonstrates expertise and realism, without requiring technical fluency.
Attendees will learn:
- What red teaming means beyond prompt injection demos
- The limitations of pre-deployment testing
- Why do misuse tactics/scenarios evolve faster than models
- How leading teams structure continuous adversarial testing
- Based loosely on the Alice Red Teaming framework (from the “Mastering AI red teaming” report, and all other reports as well)
Best for:
Corporate Strategy/ BD/ CAIOLegal, Compliance, PolicyTechnology
Sponsored by Alice
Presented by
Noam Schwartz
CEO & co-founder
Alice
Builders
Builders
Securing AI: Protecting Access, Authenticity and Autonomy
As AI systems generate content and act autonomously, attackers are targeting the seams by exploiting vulnerabilities, impersonating agents and flooding networks with synthetic data. This session explores how to defend AI infrastructure and outputs at every layer. From system-level access control to detecting fake media, learn how leaders are building trust into AI from the ground up.
Best for:
ProductOperationsLegal, Compliance, Policy
READY TO BE PART OF IT?
Don't miss out on the premier AI event of the year! Get your tickets now and be part of the future of technology!