About AI Village

Sven founded the AI Village in 2018 and has been running it ever since. He was the principal organizer of AIV’s Generative Red Team at DEFCON 31. Sven is also the founder of nbhd.ai, a startup focused on the security and integrity of datasets and the AI they build. He was previously a senior data scientist at Elastic where he built the malware model training pipeline. He has a PhD in Algebraic Topology, and a postdoc in geometric machine learning where he focused on anomaly and novelty detection.

Lauren Putvin began her security journey as a data scientist in GRC creating data driven security metrics and policy changes. She has most recently worked in security product development at various companies. She has a PhD in biomedical engineering (classifying sensor data).

Ravin is a probabilistic programming enthusiast. He brings applied experience as a data scientist at Google with prior experience at companies like SpaceX and Sweetgreen.

Ravin contributes frequently to Open Source projects such as PyMC. He also is an educator, having published textbooks and courses on the topic.

Previously, Ravin worked at SpaceX and Sweetgreen using Bayesian Statistics to assess and improve orbital rocket launches and optimize avocado preparation (among many other ingredients). He now works on the Labs team at Google on large scale generative models, with a focus on safety and security.

Ravin received his Bachelors and Masters in Engineering from Cal Poly Pomona and University of Wisconsin Madison respectively.

Brian Reeves is a Cloud Security Architect at Google, where he specializes in AI security and architecting the future of secure AI. He helps develop and externalize Google’s Secure AI Framework (SAIF), designed to guide the secure development and deployment of AI systems, and collaborates closely with internal Red Teams to proactively identify and mitigate emerging threats.

Brian brings over 15 years of expertise in building robust, compliance-driven cloud solutions for cutting-edge technologies across highly regulated industries, including HIPAA, FedRAMP, and DoD compliance regimes. He focuses on ensuring the integrity, privacy, and resilience of AI systems, bridging the gap between innovative technology and stringent compliance requirements.

Emanuel Gawrieh is a Senior Security Engineer, et cetera at Google, where he specializes in securing workloads in hybrid, distributed architectures for public sector customers and is part of the Secure AI Framework (SAIF) team advising on hardware and infrastructure security for AI Systems.

Emanuel’s has over 10 years of experience securing high performance workloads with unique hardware and infrastructure requirements across compliance regimes, and - more recently - has been working with the AI Village to prove out hardware and infrastructure configurations aiming at more efficient infrastructure for model serving, red and purple teaming, and acceleration methods best suited to the context.

Emanuel has a background in public policy. He attended Georgetown University Law Center in Washington, D.C. after studying Philosophy at Baylor University in Waco, Texas.

Bill is Technical Director of AI Product Security at ServiceNow, where he founded the company’s AI Red Team — its first cross-organizational GenAI adversarial testing function. He has spent decades operating at the leading edge of security across mainframes, the early Internet, cloud, and AI. He is an active member of the CoSAI Technical Steering Committee, the AI Alliance, and the DEFCON AI Village Steering Committee. Bill’s background spans FedRAMP, NIST AI/ML RMF, EU AI Act compliance, and secure GPU enclave architecture, and he began his career as a crypto and network technician in the U.S. Army.

With 15+ years of experience working with startups and innovation labs in AI, blockchain, and smart city projects, Tal has worked alongside over 30 startups globally, leading their cybersecurity efforts from early stages in areas of Crypto, Finance, Supply Chains, and more. A creator of highly adopted public projects, communities, and a conference speaker, Tal continues to help companies innovate with confidence and lead with assurance.

Mohamed AbuMuslim is a security researcher and offensive security engineer focused on red teaming, adversarial AI, and product security engineering. He specializes in evaluating complex systems under realistic attack conditions, with experience spanning web applications, APIs, cloud environments, enterprise infrastructure, Active Directory, and large language model integrations.

His work combines offensive security operations with research and development, with a strong emphasis on uncovering novel attack paths, improving security validation practices, and strengthening product security maturity. He has led and delivered assessments across traditional and emerging technology stacks, covering penetration testing, adversary emulation, purple teaming, static and dynamic analysis, and AI security evaluation.

Mohamed is also a speaker, educator, and community leader who regularly contributes to the security industry through conference talks, workshops, research, and public technical content. He is a Steering Committee member at AI Village, an organizer of BSides Albuquerque, a board member at OWASP Cairo, and an active contributor to practitioner education through social platforms and YouTube.