AI ethics evidence index Search
Source-linked daily record
Evidence record 58 · automatically gathered

What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection

Audio deepfake detection models determine whether speech is genuine or artificially generated, but high overall accuracy can mask substantial performance disparities across demographic groups. In this work, we investigate gender bias in audio deepfake detection using the ASVspoof5 dataset. We use ASVspoof5 under a controlled custom split designed to isolate gender-composition effects. We train attack-specific models on nine training sets with different gender compositions, ranging from female-on

Record details

Published: 10 July 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Misinformation · Finance, VC & PE
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Misinformation

Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Images

arXiv · 26 June 2026

Shared topic: Bias & fairness · Shared topic: Misinformation

Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection

arXiv · 4 August 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources

arXiv fairness query · 9 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Neutralizing Structural Inequality in the Nigerian FinTech Sector

arXiv cs.CY · 14 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

arXiv cs.AI · 14 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays

arXiv · 16 July 2026

How to cite this record

ethics.ai (10 July 2026), “What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection,” evidence record 58, https://ethics.ai/record/58 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.