Journal article · 2026 · Open access
Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails
Machine Learning, 115(6) · Published 20 May 2026 · DOI 10.1007/s10994-026-07060-8
In brief
“Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails” is a 2026 journal article by Pratik Jalan and 3 co-authors, published in Machine Learning. OpenAlex counts 22 citations as of 19 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Machine Learning.
- Citations
- 22
- Most cited in
- 2026 (22)
- Field-weighted impact
- 23.79
- References
- 178
- Authors
- 4
Abstract
Large Language Models (LLM) have demonstrated remarkable capabilities across various applications, but their deployment raises critical safety concerns as potential misuse poses significant societal risks. This survey reviews the end-to-end security and safety pipeline of LLMs, focusing on the interaction between users and model responses. We categorize the system into five key components: attacks, defenses, safety alignment, metrics and guarding mechanisms. Attacks involve crafting adversarial inputs to exploit model vulnerabilities. Defenses act as countermeasures, aiming to detect and prevent such inputs before processing. Safety alignment ensures that, even when attacks reach the model, its responses remain consistent with ethical and policy-aligned behavior. Guarding mechanisms operate post-response to flag, filter, or block unsafe outputs. Each of these stages is subject to rigorous evaluation metrics to assess their effectiveness, robustness, and limitations. As LLMs evolve toward more general-purpose intelligence, these safety considerations become increasingly critical for the development of robust and trustworthy AI systems. Finally, we highlight open challenges and future research directions to advance the security and alignment of LLMs.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jalan, P., Abishethvarman, V., Chandna, B., & Naseem, U. (2026). Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails. Machine Learning, 115(6). https://doi.org/10.1007/s10994-026-07060-8
MLA 9
Jalan, Pratik, et al. “Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails.” Machine Learning, vol. 115, no. 6, 2026. https://doi.org/10.1007/s10994-026-07060-8.
Chicago
Jalan, Pratik, Vadivel Abishethvarman, Bhavik Chandna, and Usman Naseem. 2026. “Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails.” Machine Learning 115 (6). https://doi.org/10.1007/s10994-026-07060-8.
Harvard
Jalan, P. et al. (2026) ‘Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails’, Machine Learning, 115(6). doi:10.1007/s10994-026-07060-8.
IEEE
P. Jalan, V. Abishethvarman, B. Chandna, and U. Naseem, “Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails,” Machine Learning, vol. 115, no. 6, 2026, doi: 10.1007/s10994-026-07060-8.
BibTeX
@article{jalan2026survey,
title = {{Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails}},
author = {Jalan, Pratik and Abishethvarman, Vadivel and Chandna, Bhavik and Naseem, Usman},
journal = {Machine Learning},
year = {2026},
volume = {115},
number = {6},
doi = {10.1007/s10994-026-07060-8},
url = {https://doi.org/10.1007/s10994-026-07060-8}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- large language models
- LLM safety
- adversarial attacks
- defense mechanisms
- safety alignment
- safety metrics
- guardrails
- output filtering
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Jalan, P., Abishethvarman, V., Chandna, B., & Naseem, U. (2026). Survey on LLM Safety: Attacks, Defenses, Alignment, Metrics, and Guardrails. Machine Learning, 115(6). https://doi.org/10.1007/s10994-026-07060-8
How many times has this paper been cited?
22 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Machine Learning: sign in and open the PDF from this page.
Who wrote this paper?
Pratik Jalan, Vadivel Abishethvarman, Bhavik Chandna, Usman Naseem.
What is the DOI of this paper?
10.1007/s10994-026-07060-8, permanently at https://doi.org/10.1007/s10994-026-07060-8. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.