AI risk & governance
Attacking the ready-made parts an AI system is built from - shared models, datasets or plug-in files - instead of the system itself.
Formal
Tampering with third-party parts of an AI system - model weights, add-on files such as LoRA, training data, model files that run hidden code when loaded, or copycat model pages on public hubs; OWASP lists it as LLM03:2025.
In plain English
Like buying a spare part from a shop whose name differs by one letter from your usual one - it fits and works, but someone altered it before it reached you.
In practice
A developer in a pension fund's IT department downloads a popular open model from a copycat page; loading its old-style file quietly runs code that opens a back door on the build server.
Why it matters
Most teams build on models and data they did not make and cannot fully inspect, so one poisoned download can reach every product that uses it.