Understanding and Mitigating Risks Introduced by LLM Agents
About This Session
This presentation delves into the cyber security risks posed by Large Language Model (LLM) based agents.
It will introduce a structured approach for threat modeling these agents and their frameworks, highlighting the various vulnerability classes they may introduce.
Attendees will gain insights into common threats such as data leakage, adversarial attacks, and unauthorized access.
Furthermore, the presentation will discuss effective security measures to mitigate these risks, ensuring that organizations can leverage the power of LLM agents while maintaining robust cyber security defenses.
It will introduce a structured approach for threat modeling these agents and their frameworks, highlighting the various vulnerability classes they may introduce.
Attendees will gain insights into common threats such as data leakage, adversarial attacks, and unauthorized access.
Furthermore, the presentation will discuss effective security measures to mitigate these risks, ensuring that organizations can leverage the power of LLM agents while maintaining robust cyber security defenses.
Speaker
Oliver Szimmetat
Director of Security and Compliance - Taxbit
Oliver is the Chief Privacy Office and Director of Security and Compliance at TAXbit, where he manages all aspects of security engineering, including AI security and compliance.
Before joining TAXbit in 2023, he was Head of Cloud Security at Uber. There, he built a team working on secure-by-default architecture, best practices, engineering standards, automated compliance monitoring tools, data security, and threat detection/response solutions for all of Uber’s cloud assets and engineering efforts.
Prior to that, Oliver spent over 18 years at Microsoft, where he worked in various engineering management roles contributing to Windows client security, anti-piracy, cloud security standards, security testing, and continuous delivery for all the company’s online services.
Before joining TAXbit in 2023, he was Head of Cloud Security at Uber. There, he built a team working on secure-by-default architecture, best practices, engineering standards, automated compliance monitoring tools, data security, and threat detection/response solutions for all of Uber’s cloud assets and engineering efforts.
Prior to that, Oliver spent over 18 years at Microsoft, where he worked in various engineering management roles contributing to Windows client security, anti-piracy, cloud security standards, security testing, and continuous delivery for all the company’s online services.