Rule set sha256:bd65ec208a53
PROMPT_SECURITY_EXFIL_TRAINING_DATA_EXTRACTION_001
One rule of the rule set with digest bd65ec208a532545cac038041e8bb3c2f62a09305837af00fa0917875f49eb75. An audit record that names this digest and this rule was decided by the rule as shown here. Every rule in this set.
| Rule | PROMPT_SECURITY_EXFIL_TRAINING_DATA_EXTRACTION_001 |
|---|---|
| Rule version | 8b58c3587364cef30258e0e5a4da006a96079f8789405934926fc1b1d80895cb |
| Provision | Regulation (EU) 2024/1689, Article 15(5) ELI: http://data.europa.eu/eli/reg/2024/1689/art_15/par_5/oj |
| Approval | Not approved |
rules/regulations/universal/prompt_security/exfil_training_data_extraction.yaml
- Citation
- Regulation (EU) 2024/1689, Article 15(5): High-risk AI systems shall be resilient against attempts by unauthorised third parties to alter their use, outputs or performance by exploiting system vulnerabilities. The technical solutions aiming to ensure the cybersecurity of high-risk AI systems shall be appropriate to the relevant circumstances and the risks. The technical solutions to address AI specific vulnerabilities shall include, where appropriate, measures to prevent, detect, respond to, resolve and control for attacks trying to manipulate the training data set (data poisoning), or pre-trained components used in training (model poisoning), inputs designed to cause the AI model to make a mistake (adversarial examples or model evasion), confidentiality attacks or model flaws.
- Condition
- Detects training-data extraction attacks: "repeat a word forever" divergence prompts and requests to output verbatim memorised/training text. EU AI Act Article 15. OWASP LLM01 / LLM06.
- Condition type
- regex
- Status in the file
- review