Tim Polzehl

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Speech & Audio (2)Interpretability & Mechanistic Interp (1)Eval Frameworks & Benchmarks (1)Open-Source Models & Weights (1)

Frequent co-authors

Yixuan Xiao (2)Xin Wang (2)Y. E. Kheir (2)Yassine El Kheir (2)

Papers (2)

Jul 13, 2026

Jul 13, 2026·also DFKI

Evidence Subspace Projection: Measuring How Much Evidence Explains Deepfake Detection in Self-Supervised Speech Models

Evidence Subspace Projection reveals how different factors influence deepfake detection decisions, providing a clearer understanding of model behavior in self-supervised learning.

Yixuan Xiao, Cheng-Wei Lin, Xin Wang +6

Interpretability & Mechanistic Interp Speech & Audio

Apr 9, 2026

Apr 9, 2026·also Stuttgart

DeepFense: A Unified, Modular, and Extensible Framework for Robust Deepfake Audio Detection

The best deepfake audio detectors are surprisingly biased by audio quality, speaker gender, and language, undermining their real-world reliability.

Yassine El Kheir, Y. E. Kheir, Arnab Das +13

Eval Frameworks & Benchmarks Open-Source Models & Weights Speech & Audio

Search

Tim Polzehl

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)