Also known as: Poisoning
Отравление данных — это adversarial attack, при которой malicious actor вмешивается в данные или training process, используемые для построения модели. Вставляя, изменяя или corrupting training examples, атакующий стремится manipulate model behavior, degrade performance или create targeted failures.
‘Adversarial attacks in which an adversary interferes with a model during its training stage, such as by inserting malicious training data (data poisoning) or modifying the training process itself (model poisoning).’
A side-by-side comparison of Prompt Injection and Data Poisoning. Understand how runtime instruction manipulation differs from attacks on training data or the training process.
A side-by-side comparison of Data Poisoning and Adversarial Learning. Understand how the terms differ, when each applies, and what the distinction means for AI governance, system design, or assurance evidence.