Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
3 detections
Filters
Last updated
All Time
Detection languages
2
1
Contributors
3
Categories
3
1
Platforms
3
Products / Services
3
MITRE Techniques
18,034
15,417
12,647
8,188
6,021
Detects attempts by users to extract the underlying system prompt from an LLM via prompt injection techniques or identifies successful leaks where the model's response matches a pre-calculated system prompt hash. Exposing system prompts can lead to the discovery of proprietary business logic, safety guidelines, and facilitate further adversarial jailbreaking.
Detects attempts to extract or override the system instructions of an Large Language Model (LLM) via prompt injection techniques, such as explicitly asking for the system prompt or commanding the model to ignore previous instructions.
Detects anomalous high-frequency requests to machine learning model endpoints from a single client, a pattern indicative of model extraction (stealing) attacks. This rule monitors inference request paths and success statuses to identify potential systematic input-space probing.