adversarial-ml

Open repos and models their makers tagged adversarial-ml, most starred first. The same for everyone.

Language and translationRepo

Detecting-the-Machine-A-Comprehensive-Benchmark-of-AI-Generated-Text-Detectors-Across-Architectures

This project aims to address this gap by conducting a systematic, controlled study of human versus LLM-generated text detectability using paired question–answer datasets. Rather than proposing a novel detection architecture, the focus is on analyzing detection robustness, failure modes, and the impact of adversarial humanization strategies.

  • 8
  • Jupyter Notebook
  • MIT
  • 8 mo ago
MadsDoodleTake it
Language and translationRepo

content-moderation-ai-audit

End-to-end responsible-AI audit of a DistilBERT toxicity classifier: identity-group bias audit, adversarial attacks, mitigation techniques, and a production guardrail pipeline. Built on the Jigsaw Unintended Bias in Toxicity Classification dataset.

  • 0
  • Jupyter Notebook
  • 7 mo ago
Search GitHub and Hugging Face for adversarial-ml

Get , open it once and sign in. Then come back here and press the button again.