Safety
Verification
Techniques that test a system against a stated safety requirement, such as refusing harmful requests or holding up at its limits.
11 techniques
11 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Safety Envelope Testing | Testing | Architecture/model Agnostic Requirements/black Box | Any | Safety envelope testing checks how an AI system performs at and beyond the edges of the conditions it was designed for,... | ||
| Constitutional AI Evaluation | Testing | Architecture/neural Networks/transformer/llm Requirements/white Box +1 | Text | Constitutional AI evaluation checks whether a language model follows the written principles, or 'constitution', that it... | ||
| Continual Learning Stability Testing | Testing | Architecture/model Agnostic Architecture/neural Networks +1 | Any | Continual learning stability testing checks whether a model that is updated over time with new data or tasks keeps what... | ||
| Jailbreak Resistance Testing | Testing | Architecture/neural Networks/transformer/llm Requirements/black Box | Text | Jailbreak resistance testing checks whether a language model or chatbot can be talked out of its safety rules. Testers... | ||
| Prompt Injection Testing | Testing | Architecture/neural Networks/transformer/llm Paradigm/generative +1 | Text | Prompt injection testing checks whether an AI system can be made to follow instructions its builders did not intend. In... | ||
| Toxicity Detection | Testing | Architecture/model Agnostic Architecture/neural Networks/transformer/llm +2 | Text | Toxicity detection scores a model's outputs with a classifier trained to recognise abusive language, such as insults,... | ||
| Scenario-Based Simulation Testing | Testing | Architecture/model Agnostic Requirements/black Box | Any | Scenario-based simulation testing checks an automated system, most often an automated driving system, by running it... | ||
| Operating-Point ROC Analysis | Metric | Architecture/model Agnostic Paradigm/supervised +1 | Any | Operating-point ROC analysis measures how often a classifier makes each kind of mistake at the decision threshold it... | ||
| Linear Bound Propagation Verification | Algorithmic | Architecture/neural Networks Requirements/white Box | Image Tabular | Linear bound propagation verification proves that a trained neural network meets a stated property for every input in a... | ||
| SMT-Based Neural Network Verification | Algorithmic | Architecture/neural Networks Architecture/neural Networks/feedforward +1 | Tabular | SMT-based neural network verification decides exactly whether any input in a defined region can make a trained neural... | ||
| Appropriate Reliance Measurement | Metric | Architecture/model Agnostic Requirements/black Box | Any | Appropriate reliance measurement tests whether people who receive an AI system's advice follow it when it is right and... |
Rows per page
Page 1 of 1