How to Navigate the Stiff-Arm When Protecting Your Generative AI Initiatives

NetSPI's open LLM security benchmark tests how large language models resist jailbreaks under adversarial conditions while measuring the security-usability trade-off in enterprise deployments.

Recap of a Bishop Fox fireside chat on pragmatic AI/LLM security for enterprises, covering the evolution from discriminative to generative models and practical mitigation advice from industry leaders.

A practitioner's guide to the legal boundaries of autonomous AI pentesting: why traditional authorization breaks down, and how scope, enforceable controls and evidence preservation should be designed.

YesWeHack examines three key AI pentesting concerns - scope control, harm avoidance, and traceability - and shows how its Agentic Pentest harness addresses them for safe autonomous testing.

With the rapid adoption of AI-enabled services into production applications, it’s important that organizations are able to secure the AI/ML components coming into their software supply chain. The good news is that even if you don’t have a tool specifically for scanning models themselves, you can still apply the same DevSecOps best practices to securing…

NetSPI built a deliberately vulnerable LLM chatbot to demonstrate prompt injection risks. The walkthrough shows how injected prompts enable data disclosure and, with code execution features, RCE.