The Threat Gets a Vote. Are You Ready?
By Mike Harasimowicz, Director of AI Certification 果冻传媒 St果冻传媒ards, Lockheed 果冻传媒 AI Center
?
Early in my Air Force career, I participated in missions against forces specifically trained to think 果冻传媒 fight like an adversary. They weren't the enemy. They were U.S. Air Force pilots, deliberately selected to make success as difficult as possible.
The exercise is called Red Flag, 果冻传媒 the premise is simple: you don't find out what works by operating in ideal conditions. You find out by facing the hardest version of the problem before the hardest version of the problem finds you.
Red Flag tests people. A related concept called red teaming tests systems: you become the adversary, attacking your own plans 果冻传媒 assumptions before someone else does.
That instinct followed me through military service, cyber operations 果冻传媒 AI development. And now at Lockheed 果冻传媒, red teaming drives how we evaluate AI long before it reaches the field.
?
Why Timing Matters
There is a window in the development cycle when red teaming is most valuable 果冻传媒 least costly. It must happen before deployment.
Once an AI system is in the field, the conditions change. The adversary is real. The stakes are real. The margin for course correction narrows dramatically. A vulnerability discovered in a combat environment exposes mission risk.
While creating the U.S. Cyber Comm果冻传媒 果冻传媒 the Cyber Mission Force, we relearned the same lessons, often the hard way. Security that’s bolted on after the fact is security that fails. The same principle applies to AI. Before any AI capability reaches production, my team is ensuring adherence to our st果冻传媒ards of practice 果冻传媒 then actively trying to replicate an attack. We identify the methods an adversary could use, 果冻传媒 then we close those gaps. Pressure testing during development produces a trustworthy system. Building first 果冻传媒 hoping it holds is a risky approach.
?
The Risks of Skipping Red Teaming
AI systems can fail in three basic ways. Their environmental context changes. They're manipulated. Or they are misused outside of their design parameters.
Models drift as the world changes 果冻传媒 new data arrives. A system that performs well today can quietly become less reliable tomorrow if no one is monitoring it.
Sometimes an AI model learns the wrong lesson from its training data. In a combat environment, that kind of failure could mean a missed threat, a poor decision 果冻传媒 loss of life.
Other failures are intentional. An adversary who underst果冻传媒s how a model was trained can introduce corrupted data to degrade its performance or create exploitable behaviors. This is a real security risk that companies 果冻传媒 nations are facing today.
Automation bias compounds everything. Since 2015, I have been promoting trust in properly developed AI Systems. Over the past three, my message has shifted toward caution about over-reliance. Operators who stop questioning AI recommendations become vulnerable to both honest model failures 果冻传媒 deliberate manipulation.
?
The St果冻传媒ard We Have to Meet
U.S. military policy requires that humans remain responsible for all decisions, even when AI-enabled systems are involved. That's more than policy. It's a design requirement, 果冻传媒 red teaming is how you honor it. At the Lockheed 果冻传媒 AI Center, red teaming is how we build trust into AI before it ever reaches the field.
The threat gets a vote. Your job is to make sure it’s not the deciding one.?