Organizations often place excessive faith in firewalls and perimeter security, assuming their internal environment is safe. This overlooks the fact that once a breach occurs, sensitive data is exposed. The critical question isn't just preventing entry, but protecting data once an attacker is already inside the "secure" environment.

Pursuing 100% security is an impractical and undesirable goal. Formal methods aim to dramatically raise assurance by closing glaring vulnerabilities, akin to locking doors on a house that's currently wide open. The goal is achieving an appropriate level of security, not an impossible absolute guarantee.

Since credential theft is rampant, authenticating users at login is insufficient. A modern security approach must assume breach and instead focus on anomalous behavior. It should grant access dynamically and "just-in-time" for specific tasks, revoking rights immediately after.

Experian's security strategy goes beyond simple encryption by 'sharding' data. An individual's personal information is broken into pieces and stored in separate, encrypted locations, meaning a hacker must breach multiple systems to assemble a complete profile.

Instead of relying on flawed AI guardrails, focus on traditional security practices. This includes strict permissioning (ensuring an AI agent can't do more than necessary) and containerizing processes (like running AI-generated code in a sandbox) to limit potential damage from a compromised AI.

Experian's leadership views security spending as the 'first dollar' spent. It's not a typical investment that requires an ROI justification but a non-negotiable, enabling cost for the entire business. This mindset ensures it is always prioritized, regardless of immediate financial pressures.

To prevent an AI agent from accessing personal data if compromised, set it up on a separate computer (like a Mac mini) with its own unique accounts, passwords, and even a virtual credit card for APIs. This creates a secure, sandboxed environment.

Most AI "defense in depth" systems fail because their layers are correlated, often using the same base model. A successful approach requires creating genuinely independent defensive components. Even if each layer is individually weak, their independence makes it combinatorially harder for an attacker to bypass them all.

A comprehensive AI safety strategy mirrors modern cybersecurity, requiring multiple layers of protection. This includes external guardrails, static checks, and internal model instrumentation, which can be combined with system-level data (e.g., a user's refund history) to create complex, robust security rules.