CoChat

Jailbreaking Black Box Large Language Models in Twenty Queries

Open access
Chao, Patrick, Robey, Alexander, Dobriban, Edgar, Hassani, Hamed, Pappas, George J., Wong, Eric · 2025 · 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
Cited by 193

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Abstract

There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which coax LLMs into overriding their safety guardrails. The identification of these vulnerabilities is therefore instrumental in understanding inherent weaknesses and preventing future misuse. To this end, we propose Prompt Automatic Iterative Refinement (PAIR), an algorithm that generates semantic jailbreaks with only black-box access to an LLM. PAIR—which is inspired by social engineering attacks—uses an attacker LLM to automatically generate jailbreaks for a separate targeted LLM without human intervention. In this way, the attacker LLM iteratively queries the target LLM to update and refine a candidate jailbreak. Empirically, PAIR often requires fewer than twenty queries to produce a jailbreak, which is orders of magnitude more efficient than existing algorithms. PAIR also achieves competitive jailbreaking success rates and transferability on open and closed-source LLMs, including GPT-3.5/4, Vicuna, and Gemini.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/satml64287.2025.00010

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 36 references

Research works printed but not linked: 29

  1. Wu, 2023, Bloomberggpt: A large language model for finance, arXiv preprint
  2. Korbak, 2023, Pretraining language models with human preferences, 17506
  3. Ouyang, 2022, Training language models to follow instructions with human feedback, 2022, 13
  4. Carlini, 2023, Are aligned neural networks adversarially aligned?
  5. Maus, 2023, Black box adversarial prompting for foundation models
  6. Jones, 2023, Automatically auditing large language models via discrete optimization
  7. Zou, 2023, Universal and transferable adversarial attacks on aligned language models
  8. Inan, 2023, Llama guard: Llm-based input-output safe-guard for human-ai conversations
  9. Bai, 2022, Constitutional ai: Harmlessness from ai feedback
  10. 10.18653/v1/2021.emnlp-main.696 · DOI · Paper page
  11. Bartolo, 2021, Models in the loop: Aiding crowdworkers with generative annotation assistants, arXiv preprint
  12. Huang, 2023, Catastrophic jailbreak of open-source llms via exploiting generation
  13. Mazeika, 2023, Tdc 2023 (llm edition): The trojan detection challenge
  14. Jiang, 2024, Mixtral of experts
  15. Zheng, 2023, Judging llm-as-a-judge with mt-bench and chatbot arena
  16. 2023, Gpt-4 technical report
  17. 2023, Gemini: A family of highly capable multi-modal models
  18. Jain, 2023, Baseline defenses for adversarial attacks against aligned language models, arXiv preprint
  19. Alon, 2023, Detecting language model attacks with perplexity, arXiv preprint
  20. 10.1007/978-3-319-94042-7_11 · DOI · Paper page
  21. Wang, 2019, Improving adversarial robustness requires revisiting misclassified examples, International conference on learning representations
  22. 10.1109/SP.2019.00044 · DOI · Paper page
  23. Cohen, 2019, Certified adversarial robustness via randomized smoothing, 1310
  24. Salman, 2019, Provably robust deep learning via adversarially trained smoothed classifiers, Advances in Neural Information Processing Systems, 32
  25. 10.14722/ndss.2024.24188 · DOI · Paper page
  26. 10.1109/iccv48922.2021.00760 · DOI
  27. 10.1145/3128572.3140448 · DOI · Paper page
  28. Ji, 2024, Defending large language models against jailbreak attacks via semantic smoothing, arXiv preprint
  29. Zhou, 2024, Robust prompt optimization for defending language models against jailbreaking attacks, arXiv preprint

Cited by

See all 193

Metadata

Authors
Chao, P., Robey, A., Dobriban, E., Hassani, H., Pappas, G. J., & Wong, E.
Venue
2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
Publisher
IEEE
Published
2025-04-09
Pages
23-42
OpenAlex
W4410609100
Cited by
193
References
36
FWCI
175.49
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Jailbreaking Black Box Large Language Models in Twenty Queries. https://app.cochat.ai/papers/10.1109/satml64287.2025.00010
The paper
Chao, P., Robey, A., Dobriban, E., Hassani, H., Pappas, G. J., & Wong, E. (2025). Jailbreaking Black Box Large Language Models in Twenty Queries. 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). https://doi.org/10.1109/satml64287.2025.00010

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.