Adversarial Robustness of ASR

ASR: Automatic Speech Recognition

Follow this topic Ask about this topic

Latest papers

13 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation
Oct 30, 2026Shengding Liu, Ashwin Innuganti, Qiben YanAdversarial Robustness of ASR Adversarial Attacks
Michigan State University
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Oct 6, 2026Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3Adversarial Robustness of ASR Adversarial Transferability
Department of Computer Engineering Sharif University of Technology · Department of Computer Engineering University of Isfahan
Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization
Oct 4, 2026Aref Mousavi, Shahab Sherafat, Kiarash Kiani Feriz +4Adversarial Representation Learning Speech Foundation Models
Sharif University of Technology · University of Tehran · New Uzbekistan University +1
GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition
Sep 2, 2026Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz +4Backdoor Attacks Automatic Speech Recognition
Sharif University of Technology · Isfahan University
Generative Testing of Automated Speech Recognition Systems
Jul 10, 2026Yanis Xabier Wilbrand Peña, Oliver Weißl, Andrea StoccoASR Evaluation Adversarial Robustness of ASR
Technical University of Munich Germany · Technical University of Munich & fortiss GmbH Germany
What Was That Again? Certified Robustness for Automatic Speech Recognition
Jun 26, 2026Andrew C. Cullen, Neil G. Marchant, Jiani Xie +2Automatic Speech Recognition Certified Robustness
University of Melbourne · DST Group, Adelaide
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
Jun 5, 2026Jiani Xie, Andrew C. Cullen, Paul Montague +1Streaming ASR Automatic Speech Recognition
University of Melbourne · DST Group
Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition
Jun 4, 2026Yifan Liao, Zongmin Zhang, Zhen Sun +3Adversarial Robustness of ASR Adversarial Attacks
The Hong Kong University of Science and Technology (Guangzhou) · Wuhan University
Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
May 4, 2026Sandra Arcos-Holzinger, Sarah M. Erfani, James Bailey +1Intrinsic Dimensionality Adversarial Robustness of ASR
University of Melbourne, School of Computing and Information Systems, Australia · Monash University, Department of Data Science and Artificial Intelligence, Australia · Johns Hopkins University, Center for Language and Speech Processing, USA
Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
Mar 23, 2026Matías Pizarro, Raghavan Narasimhan, Jonas Killian +1Adversarial Robustness of ASR Adversarial Robustness
Faculty of Computer Science, Ruhr University Bochum, Bochum, Germany
Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network
Mar 17, 2026Protopopov AlexeyAdversarial Examples Adversarial Robustness of ASR
Joint Stock Research and Production Company Kryptonite
Attack-Dependent Robustness of Neural Audio Codecs for Adversarial ASR
Mar 10, 2026Jordan Prescott, Thanathai Lertpetchpun, Shrikanth NarayananASR Evaluation Adversarial Robustness of ASR
Signal Analysis and Interpretation Laboratory, University of Southern California, USA
ACES: Accent Subspaces for Coupling, Explanations, and Stress-Testing in Automatic Speech Recognition
Feb 28, 2026Swapnil ParekhAdversarial Robustness of ASR Demographic Bias in ASR
Intuit

Oct 30, 2026J/K move · Enter open · S save

GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation

Shengding Liu, Ashwin Innuganti, Qiben Yan

Michigan State University

Adversarial Robustness of ASR Adversarial Attacks Adversarial Perturbations Automatic Speech Recognition

Open paper AskPDF arXiv

We present GhostPrefix, the first synchronization-free universal adversarial prefix attack against automatic speech recognition (ASR) systems. Unlike prior audio attacks, which are typically crafted per utterance, require synchronization with the victim waveform, or target narrow objectives, GhostPrefix learns a short, reusable audio segment prepended to arbitrary live speech to exert real-time control over ASR outputs without knowledge of the future utterance or temporal alignment. A key challenge is maintaining stable adversarial effects across unknown, evolving speech contexts. GhostPrefix combines token-level losses with a novel representation-level objective for stable, input-agnostic effects. GhostPrefix supports three attack modes: (i) prompted prefix attacks for semantic steering, (ii) targeted prefix attacks for transcript hijacking, and (iii) untargeted prefix attacks for transcription degradation. To remain perceptually inconspicuous, we regularize prefixes toward benign environmental-sound distributions and improve robustness against over-the-air distortions. We evaluate GhostPrefix across 13 open-source ASR models from four families. In digital settings, it achieves average attack success rates of 97.6% for prompted steering and 93.4% for targeted hijacking, while driving word error rate to 1.18 under untargeted attacks. Over the air, it achieves success rates of 91.5% and 89.5% for prompted and targeted modes, respectively. These manipulations propagate into downstream AI-assisted pipelines, including voice assistants and AI note-taking tools, causing systematic semantic misinterpretations. GhostPrefix exposes synchronization-free universal prefixes as a practical, under-explored threat to real-world ASR and downstream applications. Artifacts and demos are available at https://ghostprefix.github.io/.