AML.T0019 demonstrated

Publish Poisoned Datasets

Adversaries may Poison Training Data and publish it to a public location. The poisoned dataset may be a novel dataset or a poisoned variant of an existing open source dataset. This data may be introduced to a victim system via AI Supply Chain Compromise.

> curated attacks (1)

Research high 2024-06-06

Web-Scale Data Poisoning: The Split-View Attack

Web-scale datasets distributed as lists of URLs can be poisoned by buying expired domains behind those URLs. What researchers downloaded when the dataset was built differs from what later trainers fetch — cheaply poisoning real training corpora.