The paper introduces VoxPrivacy, a benchmark for assessing interactional privacy in Speech Language Models (SLMs). It evaluates models on a 32‑hour bilingual dataset across three difficulty tiers, revealing that most open‑source SLMs perform near random on conditional privacy decisions and even strong closed‑source systems struggle with proactive privacy inference. The authors also validate these findings on a real‑speech subset and show that fine‑tuning on a 4,000‑hour training set can improve privacy‑preserving capabilities while maintaining robustness.
By Yuxiang Wang, Hongyu Liu, Dekun Chen, Xueyao Zhang, Zhizheng Wu
The paper introduces a black-box membership inference attack framework tailored for fine-tuned text-to-speech models, addressing challenges in query generation and representation engineering. It evaluates five query types, finding recitation queries most effective, and uses multi-level speech embeddings with temporal alignment for fine-grained comparison. Experiments on CosyVoice2, F5-TTS, and XTTS-v2 trained on VCTK and British Dialect datasets show high privacy leakage, with speaker-level AUC above 0.80 and record-level AUC between 0.80 and 0.90.
By Kunlin Cai, Kaiyuan Zhang, Zihang Xiang, Jinghuai Zhang, Abeer Alwan, Fnu Suya, Yuan Tian
Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the...
The paper identifies a problem in large language model (LLM) unlearning called forget‑set misalignment, where the set of data to be forgotten does not match what the model has actually memorized. Two failure modes are described: Under Unlearning, where memorized information is omitted from the forget set, and Out‑of‑Knowledge Unlearning, where the algorithm attempts to forget knowledge the model never learned, harming performance. The authors propose CONfs, a data‑blind framework that constructs model‑aligned forget sets by eliciting the model’s memorized knowledge, and demonstrate that it achieves near‑gold standard forgetting while preserving utility better than other data‑blind methods.
By Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee
Deep Contrastive Unlearning for Language Models (DeepCUT) is a framework that removes information from fine‑tuned language models by directly optimizing their latent space. It addresses the challenge of machine unlearning in black‑box models, which has been largely overlooked by previous work that only mitigated output effects. Experiments on real‑world datasets show that DeepCUT consistently outperforms baseline methods in both effectiveness and efficiency.
By Estrid He, Tabinda Sarwar, Ibrahim Khalil, Xun Yi, Ke Wang
arXiv:2609.35952v1 Announce Type: cross
Abstract: We introduce HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising 87k real hum...
By Shen Yan, Duc Le, Irina-Elena Veliche
CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.
By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu
arXiv:2608.29943v1 Announce Type: new
Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...
By Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.
The paper introduces a two‑stage speech anonymization framework that preserves both linguistic content and acoustic identity. It replaces personally identifiable information using a generative editing model and applies a flow‑matching anonymization technique (F3‑VA) to create diverse, distinct anonymized speakers. The authors evaluate privacy with speaker verification metrics and utility by training ASR, TTS, and SER models from scratch, showing stronger privacy protection with minimal utility loss compared to existing baselines.
By Yunchong Xiao, Yuxiang Zhao, Ziyang Ma, Shuai Wang, Kai Yu, Jiachun Liao, Xie Chen
arXiv:2606. 05678v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription.
By Yifan Liao, Zongmin Zhang, Zhen Sun, Yuhui Sun, Xinhu Zheng, Xinlei He
Nuha‑Speech is a new initiative aimed at creating general‑purpose Arabic speech‑large language models (speech‑LLMs). It includes the construction of a large Arabic Speech Question‑Answering corpus with over 1.5 million samples for instruction tuning, supervised fine‑tuning of Qwen‑Omni model variants at various scales, and a systematic evaluation framework with diverse tasks and tailored metrics. The project seeks to establish foundational infrastructure for Arabic speech‑LLMs amid limited Arabic speech resources.
By Yingzhi Wang, Reem Alhazzani, Muhammad Alqurishi