Threat Modeling for Large Language Models
Large language models represent a historic opportunity to further accelerate the pace of software development. A GitLab survey reported that 67% of organizations planned to use AI in software development in the immediate future. Unfortunately, many organizations are moving quickly to adopt AI in development with little thought of security consequences. Threat modeling enable security analysts to understand the additional risks that development with LLMs represents. This session will provide an overview of AI and LLM security challenges and demonstrate how threat modeling can identify potential security weaknesses. Inspired by the OWASP Top 10 list for LLMs, the session will provide a threat modeling approach for LLMs that is straightforward to adopt in production.
NOTE: there will be door prize drawings for those that attend in person
John Dickson is CEO of Bytewhisper Security and an internationally recognized cybersecurity leader who has advised organizations on cybersecurity risk for over 25 years. John was a Principal at Denim Group where he guided that company to a successful acquisition by Coalfire in 2021. A former U.S. Air Force intelligence and cyber officer, Dickson served in the Air Force Information Warfare Center (AFIWC) and was a member of the Air Force Computer Emergency Response Team (AFCERT) in the 1990s. John has been researching and speaking about the convergence of artificial intelligence and cybersecurity and its impact on organizations since 2018.