mlsanityData to 7 Oct 2026

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

arXiv 2404.00076 ↗First posted 29 Mar 2024cs.CR cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault, attackers can train the DNN model using poisoned data, potentially degrading its performance. Another type of data poisoning attack that is extremely relevant to our investigation is label flipping, in which the attacker manipulates the labels for a subset of data. It has been demonstrated that these assaults may drastically reduce system performance, even for attackers with minimal abilities. In this study, we propose a backdoor attack named 'DirtyFlipping', which uses dirty label techniques, "label-on-label", to input triggers (clapping) in the selected data patterns associated with the target class, thereby enabling a stealthy backdoor.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 74 references that are in the map. First posted on arXiv 29 Mar 2024.

Builds on

34 of 74 references.

References · 34

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  3. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  4. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  5. 2018Spectral Signatures in Backdoor Attackscited by 457
  6. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  7. 2020Backdoor Learning: A Surveycited by 412
  8. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  9. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  10. 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learningcited by 120
  11. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 103
  12. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
22 more
  1. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 92
  2. 2021Backdoor Pre-trained Models Can Transfer to Allcited by 79
  3. 2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 76
  4. 2018Label Sanitization against Label Flipping Poisoning Attackscited by 68
  5. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  6. 2020Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferabilitycited by 65
  7. 2020AutoML to Date and Beyond: Challenges and Opportunitiescited by 63
  8. 2020Backdoor Attack against Speaker Verificationcited by 62
  9. 2018A neural attention model for speech command recognitioncited by 44
  10. 2021UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Trainingcited by 43
  11. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  12. 2020Lyapunov spectra of chaotic recurrent neural networkscited by 37
  13. 2023Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Soundcited by 28
  14. 2022Going In Style: Audio Backdoors Through Stylistic Transformationscited by 19
  15. 2019Adversarial Example Detection by Classification for Deep Speech Recognitioncited by 10
  16. 2023Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversioncited by 9
  17. 2023FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledgecited by 9
  18. 2023MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systemscited by 8
  19. 2023Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attackscited by 7
  20. 2020Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networkscited by 5
  21. 2018Deep Learning Approaches for Understanding Simple Speech Commandscited by 4
  22. 2023UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attackscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  2. 2025Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Modelscited by 1
  3. 2024Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learningcited by 0
  4. 2026When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defensecited by 0