Topic: Red Teaming AI: Offensive Security for the Modern Threat Landscape
Abstract: As artificial intelligence becomes deeply integrated into enterprise applications, security operations, business processes, and decision-making systems, it is also creating new attack surfaces and introducing unique security risks. AI systems are increasingly becoming targets for sophisticated threat actors, thus rendering traditional security assessments often insufficient to identify these emerging risks. This webinar explores the growing role of red teaming in evaluating the security, resilience, and trustworthiness of AI-enabled systems. The session will examine practical approaches for testing AI systems against evolving threats, validating security controls, assessing model behavior, and identifying weaknesses across the AI lifecycle. Participants will also learn how AI red teaming supports governance, risk management, compliance, and secure AI adoption while strengthening organizational resilience against emerging cyber threats. Join us to gain insights into how offensive security techniques can be used to simulate real-world attacks against AI models, applications, and supporting infrastructure to uncover vulnerabilities before adversaries exploit them.
Key Takeaways:
- Understand why AI systems require specialized offensive security testing and validation.
- How AI red teaming differs from traditional penetration testing and security assessments.
- Common attack techniques targeting AI models, LLMs, and generative AI applications.
- How red teaming helps identify vulnerabilities across the AI development and deployment lifecycle.
- Best practices for integrating AI security testing into GRC programs.
- Role of continuous validation and threat-informed testing in securing AI environments.
- Practical methodologies for assessing AI model behavior, robustness, and resilience.
- Aligning AI security initiatives with responsible AI and regulatory requirements.
Speaker:
Jason Ross, Product Security Principal at Salesforce
Bio: Jason Ross is a cybersecurity professional with 20+ years of experience, currently serving as Product Security Principal at Salesforce. His work focuses on adversarial testing and defense of deployed generative AI applications, agentic systems, and the large language models powering them. He specializes in prompt injection attacks and defense, model governance and security, and agent exploitation across high-stakes, high-visibility production deployments.
Beyond his role at Salesforce, Jason co-leads the OWASP GenAI Security Project Red Team Initiative and contributed to authoring the OWASP GenAI Red Teaming Guide. He is also an active contributor to the broader security community, serving as a staff member at BSidesLV and a volunteer at DEF CON.
