cs.CRNov 16, 2026

AudioTrace: File-Level Membership Detection for Audio Large Language Models

Authors: Guangzhi Sun, Xiao Zhan, Shuai Wang, Jose Such, Phil Woodland

Organizations: University of Cambridge, Cambridge, United Kingdom · School of Intelligence Science and Technology, Nanjing University, Suzhou, P.R. China · State Key Lab. of Novel Software Technology, Nanjing University, Nanjing, P.R. China · INGENIO (CSIC-Universitat Polit`ecnica de Val`encia), Valencia, Spain

Abstract

Significant privacy and copyright concerns are raised by the use of publicly available audio recordings to train audio large language models (LLMs), yet effective auditing methods remain limited. Existing membership inference attacks typically assume knowledge of complete training examples, including their associated textual supervision. In practice, however, audio recordings may be paired with privately generated transcripts, captions, or question-answer pairs that are unavailable to owners of the recordings. This motivates audio-file-level membership inference, which determines whether a recording was used for training without assuming knowledge of its training tasks and annotations. This paper provides the first systematic investigation of this challenge and introduces AudioTraceBench, a controlled benchmark comprising 1,285 audio recordings with explicit fine-tuning membership labels. Evaluations across three audio LLMs show that existing text- and video-based membership inference methods adapted to audio perform close to random guessing. To address this challenge, AudioTrace is proposed, where audio-conditioned proxy questions are generated using the target model, and membership evidence is extracted from its responses and aggregated at the recording level. Consistent improvements over existing baselines are observed, with AUROC reaching 0.60 and increasing further under increased fine-tuning exposure or adaptation capacity. Further experiments were conducted to examine the factors influencing membership signals for audio-file-level detection. These findings establish audio-file-level membership inference as a distinct and practically important auditing challenge, with AudioTrace providing an effective initial approach to this challenge.

Figures & tables

Explore similar work

CardsList
  1. Membership Inference Attacks against Large Audio Language Models

    Mar 30, 2026Jia-Kai Dong, Yu-Xiang Lin, Hung-Yi LeeMembership Inference AttacksPrivacy Leakage in Language Models

  2. TRACE: Trustworthy Reasoning from Acoustic Cues and Evidence

    Oct 15, 2026Giovana Morais, Yujin Kim, Atilay Kucukoglu +1Audio-Language Model EvaluationAudio-Language Models