import React from 'react'; import Head from '@docusaurus/Head'; import Link from '@docusaurus/Link'; import { useForcedTheme } from '@site/src/hooks/useForcedTheme'; import Layout from '@theme/Layout'; import styles from './ai-security-summit-2025.module.css'; export default function AISecuritySummit2025(): React.ReactElement { useForcedTheme('dark'); const handleSmoothScroll = (e: React.MouseEvent, targetId: string) => { e.preventDefault(); const element = document.querySelector(targetId); if (element) { const offset = 80; const elementPosition = element.getBoundingClientRect().top; const offsetPosition = elementPosition + window.pageYOffset - offset; window.scrollTo({ top: offsetPosition, behavior: 'smooth' }); } }; return (
{/* Hero Banner */}
AI Security Summit 2025
🧠 AI Security Summit 2025

The Future of AI Security

{/* Hero Content */}

Two days of leadership talks and practitioner sessions focused on real-world AI security. Catch Ian Webster on the panel "Using AI for Offensive Security Testing."

October 22-23, 2025
Westin St. Francis, San Francisco
Panel Speaker
{/* Speaker Spotlight */}

Speaker Spotlight

Panel Speaker

Ian Webster

CEO & Co-founder, Promptfoo

Ian joined industry leaders for the panel "Using AI for Offensive Security Testing," covering how teams can use automation to discover LLM and agent vulnerabilities earlier in the lifecycle.

LLM Security Red Teaming Enterprise AI
{/* Key Themes */}

Key Themes

Critical topics shaping the AI security landscape in 2025 and beyond.

🎯

Adversarial AI

Understanding how attackers exploit LLMs through prompt injection, jailbreaking, and novel attack vectors targeting foundation models.

🔐

Defense Strategies

Building robust guardrails and implementing comprehensive red teaming programs to secure AI applications at scale.

🏢

Enterprise Readiness

Navigating compliance requirements, governance frameworks, and security best practices for production AI systems.

🔮

Future Threats

Anticipating emerging vulnerabilities in multimodal models, agents, and next-generation AI architectures.

{/* Research Highlights */}

Research Highlights

01

Automated Red Teaming

Demonstrated how open-source tools can systematically discover vulnerabilities in LLM applications through automated adversarial testing.

Try it yourself →
02

Jailbreak Patterns

Analyzed common jailbreak techniques and their effectiveness across different model providers, revealing gaps in current safety measures.

View strategies →
03

Data Exfiltration

Showcased novel methods attackers use to extract sensitive information from RAG systems and enterprise chatbots.

Explore plugins →
{/* Stats */}
Oct 22–23
Dates
SF
Westin St. Francis
2
Days
1
Mission
{/* Final CTA */}

Secure Your AI

Start red teaming your LLM applications today with Promptfoo's open-source security testing framework.

Get Started Star on GitHub
{/* Footer Navigation */}
Back to All Events
); }