mlsanityData to 14 Oct 2026

A backdoor attack against LSTM-based text classification systems

arXiv 1905.12457 ↗First posted 29 May 2019cs.CRcited by 227

Not on the map. Why?

Cited by 152 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been reported to be a new type of threat. In this attack, the adversary will inject backdoors into the model and then cause the misbehavior of the model through inputs including backdoor triggers. Existed research mainly focuses on backdoor attacks in image classification based on CNN, little attention has been paid to the backdoor attacks in RNN. In this paper, we implement a backdoor attack in text classification based on LSTM by data poisoning. When the backdoor is injected, the model will misclassify any text samples that contains a specific trigger sentence into the target category determined by the adversary. The existence of the backdoor trigger is stealthy and the backdoor injected has little impact on the performance of the model. We consider the backdoor attack in black-box setting where the adversary has no knowledge of model structures or training algorithms except for small amount of training data. We verify the attack through sentiment analysis on the dataset of IMDB movie reviews. The experimental results indicate that our attack can achieve around 95% success rate with 1% poisoning rate.

Key facts. Cited by 227 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 30; 2023: 45; 2024: 62; 2025: 39; 2026: 23.

227 papers.

Sort:

By area:

  1. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  2. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  3. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 222
  4. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  5. 2023Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injectioncited by 157
  6. 2023Tensor Trust: Interpretable Prompt Injection Attacks from an Online Gamecited by 145
  7. 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learningcited by 123
  8. 2021Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoningcited by 113
  9. 2023Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Modelscited by 110
  10. 2021Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Modelscited by 105
  11. 2021RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Modelscited by 104
  12. 2023Backdoor Attacks for In-Context Learning with Language Modelscited by 96
38 more
  1. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  2. 2023Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoningcited by 92
  3. 2021Hidden Backdoors in Human-Centric Language Modelscited by 90
  4. 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 89
  5. 2021BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Modelscited by 85
  6. 2022Fisher SAM: Information Geometry and Sharpness Aware Minimisationcited by 84
  7. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  8. 2022CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarkscited by 76
  9. 2022A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarkscited by 74
  10. 2024Instructional Fingerprinting of Large Language Modelscited by 68
  11. 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 65
  12. 2023CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learningcited by 63
  13. 2024Instruction Backdoor Attacks Against Customized LLMscited by 62
  14. 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classificationcited by 60
  15. 2023TrojanPuzzle: Covertly Poisoning Code-Suggestion Modelscited by 60
  16. 2022Exploring the Universal Vulnerability of Prompt-based Learning Paradigmcited by 57
  17. 2022Fine-mixing: Mitigating Backdoors in Fine-tuned Language Modelscited by 57
  18. 2022BITE: Textual Backdoor Attacks with Iterative Trigger Injectioncited by 53
  19. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearningcited by 52
  20. 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attackscited by 49
  21. 2023Stealthy Backdoor Attack for Code Modelscited by 49
  22. 2024Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shiftcited by 49
  23. 2022A Study of the Attention Abnormality in Trojaned BERTscited by 48
  24. 2022Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defensecited by 47
  25. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 46
  26. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 44
  27. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 42
  28. 2024Test-Time Backdoor Attacks on Multimodal Large Language Modelscited by 40
  29. 2023Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Reviewcited by 39
  30. 2023Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injectionscited by 39
  31. 2021Dual-Key Multimodal Backdoors for Visual Question Answeringcited by 37
  32. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Modelscited by 36
  33. 2021Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networkscited by 34
  34. 2021Defending Against Backdoor Attacks in Natural Language Generationcited by 33
  35. 2023Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attackscited by 33
  36. 2024CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularizationcited by 33
  37. 2023Attention-Enhancing Backdoor Attacks Against BERT-based Modelscited by 32
  38. 2023RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Modelscited by 32

50 most cited of 227 All 227 (JSON)