mlsanityData to 7 Oct 2026

The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers

arXiv 2401.01537 ↗First posted 3 Jan 2024cs.CR cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

The area of Machine Learning as a Service (MLaaS) is experiencing increased implementation due to recent advancements in the AI (Artificial Intelligence) industry. However, this spike has prompted concerns regarding AI defense mechanisms, specifically regarding potential covert attacks from third-party providers that cannot be entirely trusted. Recent research has uncovered that auditory backdoors may use certain modifications as their initiating mechanism. DynamicTrigger is introduced as a methodology for carrying out dynamic backdoor attacks that use cleverly designed tweaks to ensure that corrupted samples are indistinguishable from clean. By utilizing fluctuating signal sampling rates and masking speaker identities through dynamic sound triggers (such as the clapping of hands), it is possible to deceive speech recognition systems (ASR). Our empirical testing demonstrates that DynamicTrigger is both potent and stealthy, achieving impressive success rates during covert attacks while maintaining exceptional accuracy with non-poisoned datasets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 57 of its 122 references that are in the map. First posted on arXiv 3 Jan 2024.

Builds on

57 of 122 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 518
  8. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  9. 2020Backdoor Learning: A Surveycited by 412
  10. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  11. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  12. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
38 more
  1. 2020BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvementscited by 191
  2. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  3. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  4. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 120
  5. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  6. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  7. 2021Backdoor Attacks on Self-Supervised Learningcited by 89
  8. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  9. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  10. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 65
  11. 2020Backdoor Attack against Speaker Verificationcited by 62
  12. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 61
  13. 2023LLaSM: Large Language and Speech Modelcited by 56
  14. 2019Model Agnostic Defence against Backdoor Attacks in Machine Learningcited by 52
  15. 2023A Review of Deep Learning Techniques for Speech Processingcited by 52
  16. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  17. 2020Adversarial Example Gamescited by 34
  18. 2020TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoorscited by 30
  19. 2022Untargeted Backdoor Attack against Object Detectioncited by 28
  20. 2023Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Soundcited by 28
  21. 2018LexNLP: Natural language processing and information extraction for legal and regulatory textscited by 27
  22. 2020Adversarial Machine Learning in Wireless Communications using RF Data: A Reviewcited by 25
  23. 2023Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniquescited by 22
  24. 2020A Game Theoretic Analysis of Additive Adversarial Attacks and Defensescited by 21
  25. 2023Boosting Large Language Model for Speech Synthesis: An Empirical Studycited by 21
  26. 2022Going In Style: Audio Backdoors Through Stylistic Transformationscited by 19
  27. 2022Adversarial Rademacher Complexity of Deep Neural Networkscited by 18
  28. 2021Attack on practical speaker verification system using universal adversarial perturbationscited by 17
  29. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  30. 2022Differentially Private Speaker Anonymizationcited by 16
  31. 2023Leveraging Large Language Models for Exploiting ASR Uncertaintycited by 15
  32. 2022A Survey on Backdoor Attack and Defense in Natural Language Processingcited by 13
  33. 2019A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Taskscited by 12
  34. 2018FinBrain: When Finance Meets AI 2.0cited by 10
  35. 2023Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversioncited by 9
  36. 2023MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systemscited by 8
  37. 2018Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classificationcited by 7
  38. 2022SLISEMAP: Supervised dimensionality reduction through local explanationscited by 7

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year

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

3 papers.

  1. 2024The last Dance : Robust backdoor attack via diffusion models and bayesian approachcited by 3
  2. 2025Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Modelscited by 1
  3. 2024Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimizationcited by 0