Scanning LLMs for Risk with garak: A Conversation with Leon Derczynski
garak's founder Leon Derczynski joins Vijil to talk through what happens when you point a vulnerability scanner at a language model. The conversation covers how probes and detectors work, what the failure modes look like in practice, why red teaming an LLM differs from scanning conventional software, and how the project grew into a tool with thousands of users.
.jpg)
Testimonials
“Our enterprise customers demand trust verification before deploying AI in hiring workflows. Vijil helps us ship AI agents in six weeks instead of six months while dramatically lowering compliance costs.”
“By adapting the Google Responsible Generative AI Toolkit to the needs of enterprises in various industries, Vijil provides critical capabilities for AI developers to preserve the privacy, security and safety of custom models downstream with the same rigor that went into their original release.”
