American companies are spending enormous sums to develop high-performing AI models. Distillation attacks are attempting to maliciously extract them — and nobody is doing much to stop it.
American companies are spending enormous sums to develop high-performing AI models. Distillation attacks are attempting to maliciously extract them — and nobody is doing much to stop it.
Why should we care?
I see this as a perfect real-world test. These companies can’t even protect what’s supposed to make them “valuable”. That doesn’t make it our problem. This is an easily foreseeable issue that they chose to ignore in their rush to market. They’re simply not ready. It’s their own fault.