cs.SDNov 1, 2026

GDBack: A Group-Delay Backdoor Attack on Speaker Identification via Analytic All-Pass Filtering

Authors: Bicheng Xiong, Tao Li, Chenhui Cui, Zedong Xing, Qien Li, Weiping Wen, Rubing Huang, Tsong Yueh Chen

Organizations: Xiangtan University, Xiangtan 411105, China · Beihang University, Beijing 100191, China · University of Alberta, Edmonton, AB T6G 2R3, Canada · Peking University, Beijing 100871, China · 

Abstract

Existing phase-based backdoor attacks on speaker identification rely on shared absolute phase patterns for cross-sample trigger consistency, while other audio backdoor attacks have explored shared transformations that produce input-dependent triggers. Whether phase-based triggers can achieve similar consistency without imposing identical output phase patterns remains unclear. We propose GDBack, a poison-only group-delay backdoor attack using cascaded second-order analytic all-pass filters. Applying a shared transformation across utterances ideally preserves spectral magnitude while introducing a consistent frequency-dependent phase response and group-delay contribution, without forcing identical output phases. Experiments on LibriSpeech and VoxCeleb1 with ECAPA-TDNN, x-vector, and RawNet3 achieve attack success rates above 94% across all six settings (97.00% on average), while maintaining benign accuracy close to clean models. Phase and magnitude interventions, inverse compensation, and parameter-sensitivity analyses support the role of the induced phase transformation in backdoor activation. Speech quality and content evaluations indicate limited perceptual and linguistic distortion, while robustness experiments, including real over-the-air tests, reveal varying effectiveness across conditions and architectures. These findings demonstrate that cross-sample trigger consistency can arise from a shared phase transformation without requiring a common absolute phase pattern.

Figures & tables

Explore similar work

CardsList
  1. You Are the Trigger: Speaker-Activated Backdoors

    Oct 19, 2026Nataša Krčo, Euodia Dodd, Peter Romov +1Backdoor AttacksAutomatic Speech Recognition

  2. STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling

    Mar 18, 2026Kun Wang, Meng Chen, Junhao Wang +6Backdoor Detection

  3. Natural Backdoor Attacks on Speech Recognition Models

    Jul 17, 2026Jinwen Xin, Xixiang Lyu, Jing MaBackdoor AttacksAutomatic Speech Recognition