SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact Us
Jacob Klein currently serves as the Head of Threat Intelligence at Anthropic. He leads a specialized team dedicated to detecting and investigating sophisticated real-world AI misuse cases, translating these insights into robust safeguards that protect against emerging threats. The team also actively red-teams to find novel methods to evade Anthropic Safeguards.
Before joining Anthropic, Jacob built and scaled the Trust and Safety organization at Coinbase from the ground up, where he led teams spanning threat investigations, data science, operations, and product policy as the head of Trust and Safety. Under his leadership, the organization established industry-leading practices for protecting users in the rapidly evolving cryptocurrency ecosystem.
Jacob previously served as a Strategic Threat Intelligence Manager at Google during critical inflection points, including the 2020 U.S. election and the COVID-19 pandemic. In this role, he provided strategic risk assessments to senior leadership and architected Google's approach to countering violent extremism, pioneering innovative methodologies for identifying and mitigating emerging digital threats.
Speaker / Contributor: This individual participates in SANS events, presentations, written content, or other community resources as an external contributor. They are not a SANS employee, instructor, or affiliate.
Review relevant educational resources made with contribution from this instructor.