mlsanityData to 7 Oct 2026

A Survey of Trojan Attacks and Defenses to Deep Neural Networks

arXiv 2408.08920 ↗First posted 15 Aug 2024cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their susceptibility to Neural Network Trojans (NN Trojans) maliciously injected by adversaries. This vulnerability arises due to the intricate architecture and opacity of DNNs, resulting in numerous redundant neurons embedded within the models. Adversaries exploit these vulnerabilities to conceal malicious Trojans within DNNs, thereby causing erroneous outputs and posing substantial threats to the efficacy of DNN-based applications. This article presents a comprehensive survey of Trojan attacks against DNNs and the countermeasure methods employed to mitigate them. Initially, we trace the evolution of the concept from traditional Trojans to NN Trojans, highlighting the feasibility and practicality of generating NN Trojans. Subsequently, we provide an overview of notable works encompassing various attack and defense strategies, facilitating a comparative analysis of their approaches. Through these discussions, we offer constructive insights aimed at refining these techniques. In recognition of the gravity and immediacy of this subject matter, we also assess the feasibility of deploying such attacks in real-world scenarios as opposed to controlled ideal datasets. The potential real-world implications underscore the urgency of addressing this issue effectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 91 references that are in the map. First posted on arXiv 15 Aug 2024.

Builds on

44 of 91 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  9. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  10. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  11. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  12. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
32 more
  1. 2018Spectral Signatures in Backdoor Attackscited by 457
  2. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  3. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  4. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  5. 2017Certified Defenses for Data Poisoning Attackscited by 288
  6. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 192
  7. 2020Blind Backdoors in Deep Learning Modelscited by 174
  8. 2017Neural Trojanscited by 151
  9. 2019Self-Driving Cars: A Surveycited by 147
  10. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 131
  11. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 121
  12. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 120
  13. 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 112
  14. 2020Graph Backdoorcited by 112
  15. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  16. 2021Backdoor Scanning for Deep Neural Networks through K-Arm Optimizationcited by 96
  17. 2019Defending Neural Backdoors via Generative Distribution Modelingcited by 82
  18. 2020Subpopulation Data Poisoning Attackscited by 68
  19. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66
  20. 2022The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matricescited by 62
  21. 2022BadPrompt: Backdoor Attacks on Continuous Promptscited by 59
  22. 2017Generative Poisoning Attack Method Against Neural Networkscited by 49
  23. 2019NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanationscited by 49
  24. 2018Model-Reuse Attacks on Deep Learning Systemscited by 47
  25. 2016Adversarial Diversity and Hard Positive Generationcited by 35
  26. 2019Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networkscited by 21
  27. 2019Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularizationcited by 17
  28. 2017Security Risks in Deep Learning Implementationscited by 12
  29. 2018PoTrojan: powerful neural-level trojan designs in deep learning modelscited by 9
  30. 2018Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networkscited by 8
  31. 2019Detection of Backdoors in Trained Classifiers Without Access to the Training Setcited by 7
  32. 2019Programmable Neural Network Trojan for Pre-Trained Feature Extractorcited by 3

Built on by

Not cited yet.