Skip to content
Safety

Data Poisoning

A security attack where malicious data is deliberately introduced into AI training sets to manipulate model behavior. Can cause models to produce biased outputs, bypass safety filters, or leak sensitive information.

Why it matters

Models learn from huge piles of data, often scraped from the open web, and they generally trust what they're fed. Data poisoning exploits that trust by slipping harmful or misleading examples into the training set so the model quietly learns the wrong thing. It matters because the damage is baked in during training and can be hard to spot later, making data sourcing a real security concern, not just a quality one.

In practice

Suppose attackers flood the web with pages that repeatedly pair a certain phrase with dangerous instructions, hoping the content gets scraped into a training set. If it does, the model may later respond to that phrase in the harmful way the attackers planted. This is why serious teams vet and clean their training data carefully rather than blindly ingesting everything they can find online.

Related terms

Put Data Poisoning into practice

Access 800+ AI models and 70+ tools through Vincony — start free with 100 credits.