expertise needed
security
Requires security expertise for threat analysis and mitigation
15 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Red Teaming | Process | Architecture/model Agnostic Requirements/black Box | Any | Red teaming is a structured exercise in which a team deliberately tries to make an AI system fail, so that weaknesses... | ||
| Adversarial Training Evaluation | Testing | Architecture/model Agnostic Architecture/neural Networks +1 | Any | Adversarial training evaluation tests whether a model trained on adversarial examples (inputs altered slightly to cause... | ||
| API Usage Pattern Monitoring | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | API usage pattern monitoring examines how each account uses a deployed model's API, to catch misuse that no single... | ||
| Data Poisoning Detection | Algorithmic | Architecture/model Agnostic Requirements/white Box +1 | Any | Data poisoning detection looks for training examples that an attacker has planted to change how a model behaves. The... | ||
| 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... | ||
| Model Extraction Defence Testing | Testing | Architecture/model Agnostic Requirements/black Box | Any | Model extraction defence testing checks whether a model offered through a query interface, such as a prediction API, can... | ||
| Membership Inference Attack Testing | Testing | Architecture/model Agnostic Requirements/black Box | Any | Membership inference attack testing checks whether someone with access to a trained model can tell if a particular... | ||
| Trigger-Set Model Watermarking | Algorithmic | Architecture/neural Networks Paradigm/supervised +1 | Image | Trigger-set model watermarking lets the owner of a trained classifier show later that a suspect model was copied from... | ||
| 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... | ||
| CycloneDX Machine Learning Bill of Materials | Documentation | Architecture/model Agnostic Requirements/black Box | Any | A CycloneDX ML-BOM (machine-learning bill of materials) is a machine-readable inventory of what a model is made of,... | ||
| Malicious Model-File Scanning | Testing | Architecture/model Agnostic Requirements/white Box | Any | Malicious model-file scanning checks a downloaded or received model file for code that would run when the file is... | ||
| Model Signing | Algorithmic | Architecture/model Agnostic Requirements/white Box | Any | Model signing lets the publisher of a machine-learning model attach a cryptographic signature to the model's files, so... | ||
| AutoAttack | Testing | Architecture/neural Networks Paradigm/supervised +2 | Image | AutoAttack is a fixed suite of four automated adversarial attacks, introduced by Croce and Hein (ICML 2020), that... | ||
| STRIDE-AI Threat Modelling | Process | Architecture/model Agnostic Requirements/black Box | Any | STRIDE-AI is a threat-modelling method for machine-learning (ML) systems, proposed by Mauri and Damiani (2021, extended... | ||
| C2PA Content Credentials | Algorithmic | Architecture/model Agnostic Paradigm/generative +1 | Image Text | C2PA Content Credentials attach a signed provenance record, called a manifest, to a media file, so that whoever receives... |
Rows per page
Page 1 of 1