Detections
Explore public detection logic contributed by the community across SIEM and rule languages.
1 detection
Filters
Last updated
All Time
Detection languages
1
Contributors
1
Categories
1
Products / Services
1
MITRE Techniques
18,127
15,648
12,596
8,407
6,231
Detects attempts to evade machine learning model classifications by crafting adversarial perturbations against an inference endpoint. The rule identifies suspicious patterns, including a high volume of near-identical inputs from a single client resulting in confidence scores near the model's decision boundary, which is indicative of an automated optimization loop searching for an adversarial evasion attack (MITRE ATLAS T0043).
