AI ethics evidence index Search
Source-linked daily record
Evidence record 1192 · automatically gathered

What Do Deepfake Speech Detectors Actually Hear?

Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We propose an audio-native explainability pipeline using Integrated Gradients on time-aligned self-supervised representations to localize decision evidence over time. We apply the proposed method to three WavLM-based detectors (AASIST, CA-MHFA, SLS) on ASVspoof 5 and manually annotate the highest-attribution regions to pr

Record details

Published: 9 June 2026
Source: arXiv
Category: Research
Topics: Misinformation · Transparency
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: Misinformation · Shared topic: Transparency

Ethical and Technical Limits of Deepfake Speech Datasets

arXiv · 9 June 2026

Shared topic: Misinformation · Shared topic: Transparency

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard

arXiv · 7 June 2026

Shared topic: Misinformation · Shared topic: Transparency

Accountability in name only: Fact-checking under the EU’s Code of Practice on Disinformation

HKS Misinformation Review · 7 July 2026

Shared topic: Misinformation · Shared topic: Transparency

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

arXiv · 11 May 2026

Shared topic: Misinformation · Shared topic: Transparency

AI-Generated Images: What Humans and Machines See When They Look at the Same Image

arXiv · 7 May 2026

Shared topic: Misinformation · Shared topic: Transparency

Financial Audit Assistance using Misinformation Detection and Explanation

arXiv · 20 July 2026

How to cite this record

ethics.ai (9 June 2026), “What Do Deepfake Speech Detectors Actually Hear?,” evidence record 1192, https://ethics.ai/record/1192 (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.