Agenda

This keynote explores the evolving landscape of prompt injection attacks, the risks they pose to organizations and individuals, and the innovative defenses shaping the future of AI security.

Key Topics Covered:

• Understanding Prompt Injection:

Discover what prompt injection is, how it exploits generative AI systems, and why it’s a critical concern for anyone deploying or using AI-powered solutions.

• Real-World Threats and Attack Scenarios:

Examine practical examples of prompt injection attacks, including direct and indirect techniques.

• Defensive Strategies and Best Practices:

Learn about the latest mitigation techniques, including AI red teaming and Microsoft-powered solutions.

• Building Trust in AI:

Explore how responsible AI principles, transparency, and robust security practices can help organizations and users confidently adopt generative AI technologies.

Who Should Attend:

This session is designed for business leaders, IT professionals, developers, cybersecurity experts, and anyone interested in the safe and responsible use of generative AI—regardless of industry or technical background.

Why Attend:

• Gain actionable insights into the latest AI security threats and defenses
• Understand the implications of prompt injection for your organization
• Learn how to build and deploy AI solutions that are both innovative and secure
• Connect with experts and peers shaping the future of AI safety

How can we leverage Generative AI for anomaly detection? And what benefit can we extract by using GenAI in our setup.

In this session I will address all of these issues. I will introduce you to a whole powerful family of Models you might not have heard from. I will show you how yo use these models so you can implement anomaly detection in your company in no-time!

Drawing on 2.5 years of hands-on experience building the AppSec program at Snyk, I’ll share the practical lessons, strategies, and pitfalls encountered while embedding security into modern software development workflows. We'll cover real-world approaches to secure design, developer enablement, and continuous risk reduction—all tuned for fast-moving teams.

A core focus of this talk is the growing influence of AI in the application landscape. While AI introduces new categories of risk, it also offers unprecedented opportunities to enhance security operations and development workflows. In this session, we’ll explore how to use AI as both a challenge and a tool—fighting fire with fire.

Designed for a broad audience, this talk aims to provide actionable insights whether you're a security professional, engineer, team lead, or product stakeholder.