Home » Red teaming in the AI era

Red teaming in the AI era

Main Speaker

Dor Amit

Guest Speaker

מרצה אורח

Yossi Sassi

Elli Shlomo

Oren Elimelech

Learning Tracks

Cyber Security

Course ID

42921

Date

22-06-2026

Time

Daily seminar
9:00-16:30

Location

Daniel Hotel, 60 Ramat Yam st. Herzliya

Overview

Red teaming as we knew it is gone. AI has reshaped both sides of the equation – expanding the attack surface defenders must assess, while changing the economics and speed of offensive operations. This seminar gives security leaders a structured view of the new risk landscape, how to measure and evaluate these risks and the mindset shift required to run a credible red team program in the AI era.

Who Should Attend

CISOs and Security Directors
IT Managers and Technical Decision Makers
Red Team and Offensive Security Leads

Prerequisites

Course Contents

Red Teaming with AI – New Adversarial Capabilities, New Risk Exposure
- The collapse of attacker cost and time: how to reassess likelihood and frequency in your risk models
- New classes of exposure (AI-driven social engineering, automated exploitation, adaptive malware) and how to measure readiness against them
- Evolving the red team mindset: from point-in-time engagements to continuous, AI-accelerated adversary emulation

Red Teaming of AI – A New Asset Class with Non-Deterministic Risk
- Why AI systems don’t behave like traditional software: probabilistic failure modes, emergent behavior and expanded blast radius
- Risk categories to evaluate input manipulation, data and model integrity and agentic autonomy
- Measuring what matters: risk scoring for AI systems, mapping to MITRE ATLAS, OWASP LLM Top 10 and NIST AI RMF

Key Takeaways
- A clear framework for identifying and prioritizing AI-era risks – both offensive and defensive
- Practical approaches to measuring and evaluating risks that traditional metrics miss
- A modern red team mindset built for probabilistic systems and AI-accelerated adversaries