Introducing OSAI: OffSec's 24-Hour AI Red Team Challenge

OSAI is the definitive antidote to superficial understanding while emphasizing the irreplaceable value of human expertise in the age of AI.

NEW YORK, Jun 16, 2026 /PRNewswire/ -- As organizations increasingly integrate generative AI, machine learning models, and autonomous AI applications, the cybersecurity attack surface is expanding rapidly. Traditional penetration testing approaches, designed for conventional IT environments, are proving insufficient for the novel risks introduced by AI systems, data pipelines, and orchestration frameworks. To equip security professionals with the specialized skills needed for this evolving landscape, OffSec introduces Advanced AI Red Teaming (AI-300 course/ OSAI certification). For comprehensive details on this AI cybersecurity training, certification and enrollment, visit https://www.offsec.com/courses/ai-300/.

Addressing the Expanding AI Attack Surface

"In the AI age where autonomous AI agents are rapidly deployed across dev, test, and production environments, OffSec maintains its fundamental belief in the 'Human Differential'—the acute adversarial judgment calls that humans need to make to identify logic flaws along with LLM limitations to achieve business objectives in cybersecurity," said Ning Wang, CEO. "The Advanced AI Red Teaming course and certification (OSAI) teaches people how to do their job effectively in attacking AI agents and LLM models, enabling the cyber professionals to demonstrate their hands-on mastery of offensive security techniques, approaches, and mindset critical for evaluating AI systems."

The development of OSAI stems from the understanding that while automation can replicate processes, it cannot replicate the nuanced perspective of a human operator. OffSec emphasizes the human-in-the-loop—the critical ability to identify logic flaws in Large Language Models and complex AI systems that automated scanners might overlook. This new course and certification builds on OffSec's established authority in cybersecurity training, drawing from the expertise of the same authors behind the OSCP certification, ensuring a rigorous, practical approach to AI security.

Mastering Offensive AI Security Techniques

Advanced AI Red Teaming (AI-300) is designed to teach learners how to apply an adversary mindset to modern artificial intelligence technology. The curriculum combines proven cybersecurity methodologies with offensive techniques specifically tailored for AI applications, deep learning systems, and emerging AI technologies. Participants will learn how real attackers identify weaknesses in AI-enabled environments, manipulate model behavior, and compromise the infrastructure supporting modern AI deployments. The training focuses on practical skills to simulate adversarial attacks and analyze the impact of vulnerabilities across complex AI ecosystems.

Professionals will achieve hands-on expertise in AI cybersecurity while building skills in securing AI, cloud security, and modern AI technologies, including:

• Attacking AI Agents
• Exploiting multi-agent workflows and orchestration frameworks
• Exploiting RAG pipelines
• Attacking Embedding Models
• Supply Chain Attacks in LLMs

Hands-On Expertise and Certification

The course emphasizes hands-on AI cybersecurity training labs that simulate real-world environments where AI systems operate alongside traditional infrastructure. Learners engage with enterprise-style AI architectures, including LLMs, vector databases, multi-agent systems, model orchestration frameworks, and cloud security environments supporting AI infrastructure. This practical experience allows professionals to evaluate AI-enabled systems from an attacker's perspective, supporting real-world security operations and incident response readiness.

The training culminates in the OffSec AI Red Teamer (OSAI) certification exam, a rigorous 24-hour practical red team engagement. Successful candidates earn the OSAI certification, demonstrating practical expertise in assessing and exploiting modern AI systems. OSAI is intended for experienced cybersecurity professionals, including penetration testers, red teamers, and security engineers, seeking to expand their expertise into AI security and machine learning security roles. 

Advanced AI Red Teaming course and certification  is available for purchase, for practitioners and enterprise organizations.

About OffSec

OffSec is the world's leading provider of high-fidelity cybersecurity training and certifications. Built on a foundation of excellence, integrity, and the relentless "Try Harder" ethos, OffSec empowers individuals and organizations to outsmart evolving cyber threats through rigorous, hands-on learning.

From its beginnings to today, OffSec has set the "Gold Standard" for cybersecurity proficiency, earning global recognition and the implicit trust of the world's most elite security teams. With a comprehensive ecosystem ranging from the industry-defining OSCP to the cutting-edge OSAI (OffSec AI Red Teamer), OffSec is the definitive benchmark for validating real-world technical skills in an increasingly automated world.

For more information, visit www.offsec.com and follow the conversation on LinkedIn and X (Twitter).

SOURCE OffSec