detector_benchmark.detector.watermark_detector¶
Classes¶
Module Contents¶
- class detector_benchmark.detector.watermark_detector.WatermarkDetector(watermarking_scheme: detector_benchmark.watermark.auto_watermark.AutoWatermark, detection_threshold: float)¶
Bases:
detector_benchmark.detector.detector.Detector- watermarking_scheme¶
- detection_threshold¶
- detect(texts: list[str], batch_size: int, detection_threshold: float) tuple[list[int], list[float], list[int]]¶
Detect the if the texts given as input are watermarked (label 1) or not (label 0).
Parameters:¶
- texts: list[str]
The texts to detect
- batch_size: int
The batch size
- detection_threshold: float
The threshold to use for the detection
Returns:¶
- tuple[list[int], list[float], list[int]]
The predictions, the logits for the positive class, and the predictions at the threshold