mlsanityData to 7 Oct 2026

A Survey of Neural Trojan Attacks and Defenses in Deep Learning

arXiv 2202.07183 ↗First posted 15 Feb 2022cs.CR cs.AI cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that deep learning can be manipulated by embedding Trojans inside it. Unfortunately, pragmatic solutions to circumvent the computational requirements of deep learning, e.g. outsourcing model training or data annotation to third parties, further add to model susceptibility to the Trojan attacks. Due to the key importance of the topic in deep learning, recent literature has seen many contributions in this direction. We conduct a comprehensive review of the techniques that devise Trojan attacks for deep learning and explore their defenses. Our informative survey systematically organizes the recent literature and discusses the key concepts of the methods while assuming minimal knowledge of the domain on the readers part. It provides a comprehensible gateway to the broader community to understand the recent developments in Neural Trojans.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 81 of its 117 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

81 of 117 references.

References · 81

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  3. 2018How To Backdoor Federated Learningcited by 745
  4. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  5. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  6. 2018Spectral Signatures in Backdoor Attackscited by 457
  7. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  8. 2020Backdoor Learning: A Surveycited by 412
  9. 2019Hidden Trigger Backdoor Attackscited by 359
  10. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  11. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  12. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
38 more
  1. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  2. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  3. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 258
  4. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 237
  5. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  6. 2019A backdoor attack against LSTM-based text classification systemscited by 214
  7. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 192
  8. 2020Blind Backdoors in Deep Learning Modelscited by 174
  9. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  10. 2017Neural Trojanscited by 151
  11. 2018SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systemscited by 148
  12. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 147
  13. 2019Universal Litmus Patterns: Revealing Backdoor Attacks in CNNscited by 143
  14. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  15. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 131
  16. 2020Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscited by 130
  17. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  18. 2020Backdoor Attacks Against Deep Learning Systems in the Physical Worldcited by 129
  19. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  20. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  21. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 121
  22. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 120
  23. 2020RAB: Provable Robustness Against Backdoor Attackscited by 115
  24. 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 112
  25. 2020Graph Backdoorcited by 112
  26. 2021Backdoor Scanning for Deep Neural Networks through K-Arm Optimizationcited by 96
  27. 2019Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacycited by 93
  28. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  29. 2020Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxificationcited by 93
  30. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 92
  31. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  32. 2019Defending Neural Backdoors via Generative Distribution Modelingcited by 82
  33. 2020On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shapingcited by 82
  34. 2020Rethinking the Trigger of Backdoor Attackcited by 76
  35. 2020DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentationcited by 75
  36. 2020On Certifying Robustness against Backdoor Attacks via Randomized Smoothingcited by 74
  37. 2019Bypassing Backdoor Detection Algorithms in Deep Learningcited by 69
  38. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 5; 2025: 1; 2026: 1.

17 papers.

Sort:

By area:

  1. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  2. 2023BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Modelscited by 37
  3. 2023Attention-Enhancing Backdoor Attacks Against BERT-based Modelscited by 32
  4. 2024Preference Poisoning Attacks on Reward Model Learningcited by 14
  5. 2024Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internalscited by 13
  6. 2022Attention Hijacking in Trojan Transformerscited by 6
  7. 2022Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationcited by 4
  8. 2024DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-Worldcited by 3
  9. 2025An Experimental Study of Trojan Vulnerabilities in UAV Autonomous Landingcited by 3
  10. 2023Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifierscited by 2
  11. 2023MLHOps: Machine Learning for Healthcare Operationscited by 2
  12. 2022Understanding Impacts of Task Similarity on Backdoor Attack and Detectioncited by 1
5 more
  1. 2024Resilience in Knowledge Graph Embeddingscited by 1
  2. 2023Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillationcited by 0
  3. 2023Mitigating Backdoors within Deep Neural Networks in Data-limited Configurationcited by 0
  4. 2024Solving Trojan Detection Competitions with Linear Weight Classificationcited by 0
  5. 2026Backdoor Learning in Language Models and Vision-Language Modelscited by 0