Archive - Beyond Fault Lines

Can we Trust Zero Trust?

What AI Changes About Security Boundaries

Jan 23 • Munib Shah

Assume the Model will be social engineered. Design so that it doesn’t matter

Why Trying to Protect the Model Is the Wrong Starting Point

Jan 15 • Munib Shah

What Hardening Atlas Reveals About the Real Risks of Prompt Injection

What continuous hardening means for AI agents operating on the open web

Jan 9 • Munib Shah

Using the OWASP GenAI Security Project’s AI Threat Defense Compass to Deploy Microsoft Copilot Securely

How do we capture the benefits of AI while avoiding the ways it can cause harm?

Jan 8 • Munib Shah

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts