mlsanityData to 14 Oct 2026

Threats to Pre-trained Language Models: Survey and Taxonomy

arXiv 2202.06862 ↗First posted 14 Feb 2022cs.CRcited by 19

Not on the map. Why?

Abstract (arXiv)

Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the adoption of PTLMs. In this survey, we comprehensively systematize recently discovered threats to PTLM systems and applications. We perform our attack characterization from three interesting perspectives. (1) We show threats can occur at different stages of the PTLM pipeline raised by different malicious entities. (2) We identify two types of model transferability (landscape, portrait) that facilitate attacks. (3) Based on the attack goals, we summarize four categories of attacks (backdoor, evasion, data privacy and model privacy). We also discuss some open problems and research directions. We believe our survey and taxonomy will inspire future studies towards secure and privacy-preserving PTLMs.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Feb 2022.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 12; 2024: 2; 2025: 3.

19 papers.

Sort:

By area:

  1. 2023Large Language Model Alignment: A Surveycited by 243
  2. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  3. 2022CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarkscited by 76
  4. 2024Large Language Model Safety: A Holistic Surveycited by 59
  5. 2023From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?cited by 55
  6. 2023Citation: A Key to Building Responsible and Accountable Large Language Modelscited by 20
  7. 2023METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualitiescited by 20
  8. 2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
  9. 2023Backdoor Attacks with Input-unique Triggers in NLPcited by 12
  10. 2023A Systematic Survey of Prompt Engineering on Vision-Language Foundation Modelscited by 12
  11. 2025Metamorphic Testing of Large Language Models for Natural Language Processingcited by 12
  12. 2023ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmapscited by 8
7 more
  1. 2023UOR: Universal Backdoor Attacks on Pre-trained Language Modelscited by 8
  2. 2023How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Surveycited by 4
  3. 2022Understanding Impacts of Task Similarity on Backdoor Attack and Detectioncited by 1
  4. 2023PeaTMOSS: Mining Pre-Trained Models in Open-Source Softwarecited by 1
  5. 2024LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameterscited by 1
  6. 2025The Ripple Effect: On Unforeseen Complications of Backdoor Attackscited by 1
  7. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Privacy Risks and Protection in Large Language Models
  2. 2024Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey
  3. 2024Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
  4. 2025A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
  5. 2025Attack and defense techniques in large language models: A survey and new perspectives
  6. 2025Security Concerns for Large Language Models: A Survey
  7. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
  8. 2024Security and Privacy Challenges of Large Language Models: A Survey