No article text was recorded for this version.
imperceptible audio perturbations
Version 2 of 2168 papers268 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Adversarial Example Attacks against ASR Systems: An Overview
- Blog: Adversarial Example Attacks against ASR Systems: An Overview
- Blog: Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
- Blog: Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
- Blog: Defense Against Adversarial Attacks on Spoofing Countermeasures of ASV
- Blog: Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
- Blog: Multidiscriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems
- Blog: TrustSER: On the Trustworthiness of Fine-tuning Pre-trained Speech Embeddings For Speech Emotion Recognition
- Blog: Characterizing the Adversarial Vulnerability of Speech self-Supervised Learning
- Blog: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
- Blog: Adversarial Black-Box Attacks on Automatic Speech Recognition Systems Using Multi-Objective Evolutionary Optimization
- Blog: Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
- Blog: The Impact of Dialect Variation on Robust Automatic Speech Recognition for Catalan
- Blog: Universal Adversarial Perturbations for Speech Recognition Systems
- Blog: SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems
- Blog: On Adversarial Attacks In Acoustic Localization
- Blog: Universal Adversarial Perturbations for Speech Recognition Systems
- Blog: Tubes among us: Analog attack on automatic speaker identification
- Blog: CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition
- Blog: Devil's Whisper: A General Approach for Physical Adversarial Attacks against Commercial Black-box Speech Recognition Devices
- Blog: AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
- Blog: Universal Adversarial Attacks on Spoken Language Assessment Systems
- Blog: Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
- Blog: Recent improvements of ASR models in the face of adversarial attacks
- Blog: Neural Predictor for Black-Box Adversarial Attacks on Speech Recognition
- Blog: ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio
- Blog: Hear "No Evil", See "Kenansville"*: Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems
- Blog: Adversarial Attacks on ASR Systems: An Overview
- Blog: Characterizing Audio Adversarial Examples Using Temporal Dependency
- Blog: Comparative study on noise-augmented training and its effect on adversarial robustness in ASR systems
- Blog: Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
- Blog: Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy
- Blog: Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
- Blog: Evaluation of Audio Language Models for Fairness, Safety, and Security
- Blog: Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time
- Blog: E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
- Blog: Adversarial attack on Speech-to-Text Recognition Models
- Blog: FraudWhistler: A Resilient, Robust and Plug-and-play Adversarial Example Detection Method for Speaker Recognition
- Blog: What You Read Isn’t What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
- Blog: Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
- Blog: Tiny noise, big mistakes: Adversarial perturbations induce errors in \n Brain-Computer Interface spellers
- Blog: DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
- Blog: Universal Adversarial Perturbations Generative Network for Speaker Recognition
- Blog: Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models
- Blog: TTSlow: Slow Down Text-to-Speech with Efficiency Robustness Evaluations
- Blog: Adversarial Attacks on GMM i-vector based Speaker Verification Systems
- Blog: There is more than one kind of robustness: Fooling Whisper with adversarial examples
- Blog: Adversarial Attacks on Text-dependent Speaker Verification System
- Blog: Characterizing the adversarial vulnerability of speech self-supervised learning
- Blog: SPIRIT: Patching Speech Language Models against Jailbreak Attacks
- Blog: Robust sensor fusion algorithms against voice command attacks in autonomous vehicles
- Blog: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
- Blog: Adversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey
- Blog: Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time
- Blog: Preventing sensitive-word recognition using self-supervised learning to preserve user-privacy for automatic speech recognition
- Blog: TRUST-SER: On The Trustworthiness Of Fine-Tuning Pre-Trained Speech Embeddings For Speech Emotion Recognition
- Blog: SPIRIT: Patching Speech Language Models against Jailbreak Attacks
- Blog: Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking
- Blog: Are Deep Speech Denoising Models Robust to Adversarial Noise?
- Blog: Detecting Audio Attacks on ASR Systems with Dropout Uncertainty
Showing 60 of 168 papers.
History & citation
Current · Permanent link
- Audio Purification through Generative Re-synthesis merged into this direction (50% overlap)
- transcription discrepancy detection split from this direction (50% overlap)
- imperceptible adversarial perturbations split from this direction (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_imperceptible_audio_perturbations_41832d7c,
title = {imperceptible audio perturbations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/imperceptible-audio-perturbations/rdr_41832d7cc1614da290fe7e0497446bfc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_imperceptible_audio_perturbations_41832d7c_v2,
title = {imperceptible audio perturbations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/imperceptible-audio-perturbations/rdr_41832d7cc1614da290fe7e0497446bfc/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}