# gradient

5 articlestagged with “gradient”

Gradient-Based Data Poisoning

Using gradient information to craft maximally effective poisoned samples that achieve attacker objectives with minimal data modification.

Extracting training data from gradient updates in federated and collaborative learning settings.

Use gradient information from open-source models to craft optimally poisoned training examples.

Using systematic search and optimization algorithms to discover maximally effective adversarial prompts for specific target behaviors.

Using gradient information to craft optimally adversarial training examples for targeted model manipulation.