Отравление данных

Also known as: Poisoning

Caesar AI Atlas Definition

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.

Other Definitions

Отравление данных Source

A type of cyberattack in which a malicious actor intentionally compromises a training dataset used by an AI model to influence or manipulate the operation of that model.

Отравление данных Source

‘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).’

Concept Comparisons

Attack / FailureLlm Security

Prompt Injection vs Data 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.