AI for Secure React Developing with Prompt Engineering & Automate AI Red teaming

NOTE: The location for this event is Hera Hub which we've used in the past.

• No ID check necessary

Abstract
Talk 1: Leveraging AI for Secure React Development with Effective Prompt Engineering
Practical and usable advice on how to harness the power of AI to create secure React applications by using prompt engineering best practices. We will discuss practical methods for guiding AI models to produce safe, high-quality React code that reduces common vulnerabilities, such as cross-site scripting (XSS) and injection flaws.

Attendees will learn foundational techniques for crafting precise prompts, incorporating secure coding patterns, and validating AI-generated outputs.
By the end of this session, you will be equipped with actionable steps to integrate AI-driven development into your workflow and strengthen the overall security of your React and other software projects.

Talk 2: Automate AI Red Teaming with PyRIT
As organizations accelerate their adoption of generative AI, the security landscape is shifting rapidly. This session introduces the OWASP Top 10 for LLM Applications, providing a clear framework for understanding the most common and impactful risks in AI-integrated systems, from prompt injection and insecure plugin design to data leakage and model wallet attacks.

We will explore real-world implications for enterprises deploying LLMs in production, focusing on the unique attack surfaces these systems introduce. Attendees will gain practical insight into how to think about threats in an AI context, including misalignment between model behavior and policy.

The session includes a live demo of Microsoft’s PyRIT tool (Python Risk Identification Tool). This open-source framework enables automated AI red teaming, helping security teams validate LLM guardrails and expose risky model behaviors at scale. We’ll walk through how to define attack goals, run scenarios, and analyze model responses.