Open Sesame! Universal Black-Box Jailbreaking of Large Language Models
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Large language models (LLMs), designed to provide helpful and safe responses, often rely on alignment techniques to align with user intent and social guidelines. Unfortunately, this alignment can be exploited by malicious actors seeking to manipulate an LLM’s outputs for unintended purposes. In this paper, we introduce a novel approach that employs a genetic algorithm (GA) to manipulate LLMs when model architecture and parameters are inaccessible. The GA attack works by optimizing a universal adversarial prompt that—when combined with a user’s query—disrupts the attacked model’s alignment, resulting in unintended and potentially harmful outputs. Our novel approach systematically reveals a model’s limitations and vulnerabilities by uncovering instances where its responses deviate from expected behavior. Through extensive experiments, we demonstrate the efficacy of our technique, thus contributing to the ongoing discussion on responsible AI development by providing a diagnostic tool for evaluating and enhancing alignment of LLMs with human intent. To our knowledge, this is the first automated universal black-box jailbreak attack.
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.
Integrity signals
Registry
Cites
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.
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
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Training Language Models to Follow Instructions with Human Feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2011 · Cited by 3,117
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410
Evasion Attacks against Machine Learning at Test Time
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., & Roli, F. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40994-3_25 · Cited by 890
Galactica: A Large Language Model for Science
Taylor, R., Kardas, M., Cucurull, G., Scialom, T., Hartshorn, A., Saravia, E., Poulton, A., Kerkez, V., & Stojnic, R. (2022) · arXiv · doi:10.48550/arxiv.2211.09085 · Cited by 605
Improving alignment of dialogue agents via targeted human judgements
Glaese, A., McAleese, N., Trębacz, M., Aslanides, J., Firoiu, V., Ewalds, T., Rauh, M., Weidinger, L., Chadwick, M., Thacker, P., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.14375 · Cited by 134
Dentella, V., Günther, F., & Leivada, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2309583120 · Cited by 67
Cited by
Security and Privacy Challenges of Large Language Models: A Survey
Das, B. C., Amini, M. H., & Wu, Y. (2025) · ACM Computing Surveys · doi:10.1145/3712001 · Cited by 445
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Andriushchenko, M., Croce, F., & Flammarion, N. (2024) · arXiv · doi:10.48550/arxiv.2404.02151 · Cited by 396
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Zhu, S., Zhang, R., An, B., Wu, G., Barrow, J., Wang, Z., Huang, F., Nenkova, A., & Sun, T. (2023) · arXiv · doi:10.48550/arxiv.2310.15140 · Cited by 230
When LLMs meet cybersecurity: a systematic literature review
Zhang, J., Bu, H., Wen, H., Liu, Y., Fei, H., Xi, R., Li, L., Yang, Y., Zhu, H., & Meng, D. (2025) · Cybersecurity · doi:10.1186/s42400-025-00361-w · Cited by 383
Zeng, Y., Lin, H., Zhang, J., Yang, D., Jia, R., & Shi, W. (2024) · arXiv · doi:10.48550/arxiv.2401.06373 · Cited by 174
Metadata
- Authors
- Lapid, R., Langberg, R., & Sipper, M.
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2024-08-14
- Volume
- 14
- Issue
- 16
- Pages
- 7150
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4401615053
- Cited by
- 71
- References
- 10
- FWCI
- 10.57
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.