LLM Detector benchmarkΒΆ

Documentation for detector benchmark.

FeaturesΒΆ

  • Generating an (adversarial) benchmark with a specific configuration, used for testing detectors.

  • Detectors and watermark detection benchmarking (adversarial + non-adversarial)

  • Modularity: possible to add new datasets, detectors, attacks and watermarking schemes without much effort