arXiv Machine Learning
Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
1d ago
VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
arXiv:2601.19956v2 Announce Type: replace-cross Abstract: As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge eme...
arXiv AI
Jul 7
NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization
arXiv:2607. 03985v1 Announce Type: cross Abstract: Advanced neural technologies in speech synthesis and voice conversion (VC) have introduced severe risks to personal privacy, necessitating robust Speaker Anonymization Systems (SAS).
arXiv AI
1d ago
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
arXiv:2604.17000v1 Announce Type: cross Abstract: The growing reliance on large-scale speech data has made privacy protection a critical concern. However, existing anonymization approaches often degr...
arXiv AI
Jun 6
Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition
arXiv:2606. 05678v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription.
arXiv AI
Jun 4
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
arXiv Machine Learning
Aug 27
Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models
The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.