When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

arXiv:2605.28211 · cs.CL · Submitted 2026-05-27 · Read on arXiv

cs.CL

Submitted: 2026-05-27

Updated: 2026-09-22

Terminology

• Accuracy — 34× in this paper · explained in 1 episode
• Fine-Tuning — 30× in this paper · explained in 5 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Adversarial Examples — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Adversarial Context — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• IEEE Automatic Speech Recognition and Understanding Workshop — 1× in this paper
• Personalization — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
• LoRA: Low-Rank Adaptation of Large Language Models
• On The Landscape of Spoken Language Models: A Comprehensive Survey
• Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Gemma 3 Technical Report
• Qwen2.5-Omni Technical Report
• OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering