mlsanityData to 14 Oct 2026

MSDT: Masked Language Model Scoring Defense in Text Domain

arXiv 2211.05371 ↗First posted 10 Nov 2022cs.CLcited by 0

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models from various websites empowered the public users as well as some major institutions to give a momentum to their real-life application. However, it was recently proven that models become extremely vulnerable when they are backdoor attacked with trigger-inserted poisoned datasets by malicious users. The attackers then redistribute the victim models to the public to attract other users to use them, where the models tend to misclassify when certain triggers are detected within the training sample. In this paper, we will introduce a novel improved textual backdoor defense method, named MSDT, that outperforms the current existing defensive algorithms in specific datasets. The experimental results illustrate that our method can be effective and constructive in terms of defending against backdoor attack in text domain. Code is available at https://github.com/jcroh0508/MSDT.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 13 of its 19 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

13 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models6 Oct
  2. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger26 May

Other references · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  7. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  8. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  9. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  10. 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 263
  11. 2020Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identificationcited by 86

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Defense Against Syntactic Textual Backdoor Attacks with Token Substitution
  2. 2026Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
  3. 2025A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
  4. 2023RobustNLP: A Technique to Defend NLP Models Against Backdoor Attacks
  5. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
  6. 2023Backdoor Attacks for In-Context Learning with Language Models
  7. 2025Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
  8. 2023Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review