Author

Shaz Furniturewala

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Sep 2025

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content

Demographic analysis across 20 Jigsaw and 13 ToxiGen minority groups reveals structurally unequal adversarial vulnerability, exposing mechanistically traceable fairness gaps in current toxicity classifiers.

Shaz Furniturewala, A. Zubiaga · arXiv.org · 1 citation