mlsanityData to 14 Oct 2026

Going In Style: Audio Backdoors Through Stylistic Transformations

arXiv 2211.03117 ↗First posted 6 Nov 2022cs.CR cs.LG cs.SDcited by 21

Not on the map. Why?

Abstract (arXiv)

This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects. We first formalize stylistic triggers - currently missing in the literature. Second, we explore how to develop stylistic triggers in the audio domain by proposing JingleBack. Our experiments confirm the effectiveness of the attack, achieving a 96% attack success rate. Our code is available in https://github.com/skoffas/going-in-style.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 6 Nov 2022.

Builds on

17 of 24 references.

References · 17

  1. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  4. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  5. 2017Adversarial Attacks on Neural Network Policiescited by 320
  6. 2019Label-Consistent Backdoor Attackscited by 296
  7. 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
  8. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  9. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  10. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  11. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  12. 2020Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxificationcited by 95
5 more
  1. 2020Backdoor Attack against Speaker Verificationcited by 66
  2. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 44
  3. 2022StyleFool: Fooling Video Classification Systems via Style Transfercited by 20
  4. 2017Audio style transfercited by 15
  5. 2022Dynamic Backdoors with Global Average Poolingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 5; 2026: 4.

21 papers.

Sort:

By area:

  1. 2023Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Soundcited by 30
  2. 2023Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversioncited by 10
  3. 2023FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledgecited by 10
  4. 2023SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classificationcited by 6
  5. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  6. 2024Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognitioncited by 5
  7. 2024A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attackscited by 4
  8. 2023Breaking Speaker Recognition with PaddingBackcited by 3
  9. 2024The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggerscited by 3
  10. 2024BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluationcited by 3
  11. 2025CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarkingcited by 3
  12. 2024EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Modelscited by 2
9 more
  1. 2023Invisible Threats: Backdoor Attack in OCR Systemscited by 1
  2. 2025Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognitioncited by 1
  3. 2025Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Modelscited by 1
  4. 2025Multi-Target Backdoor Attacks Against Speaker Recognitioncited by 1
  5. 2026STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profilingcited by 1
  6. 2025SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Modelscited by 0
  7. 2026TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecastingcited by 0
  8. 2026Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attackcited by 0
  9. 2026From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
  2. 2026Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
  3. 2026Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
  4. 2025Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers
  5. 2025Multilingual and Multi-Accent Jailbreaking of Audio LLMs
  6. 2026When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
  7. 2025AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
  8. 2024Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach