Corrupting training data to manipulate model behavior or introduce vulnerabilities.
This concept is essential for understanding specialized ai topics and forms a key part of modern AI systems.
Related Concepts
- Security
- Backdoor Attack
- Training
Standard 2 stops to get here · leads to 1
Data Poisoning
Corrupting training data to manipulate model behavior or introduce vulnerabilities.
Your route here
2 stops · basics first
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Training Data ✓ understood
The examples a model learns its weights from, kept separate from the validation and test data used to check how well it generalizes.
- Data Poisoning · you are here ✓ understood
Where it sits
Explore nearby
Shipping AI Backdoor Attack Maliciously training models to behave normally except when specific triggers are present. Shipping AI Adversarial Attack Intentionally crafted inputs designed to fool AI models into making incorrect predictions, exposing vulnerabilities. Evaluation Robustness A model's ability to maintain performance under distribution shifts, adversarial attacks, or noisy inputs. Shipping AI AI Safety Research and practices aimed at ensuring AI systems are safe, reliable, and beneficial, especially as capabilities increase.
In the research
All papers →A paper that builds on Data Poisoning .
