Concepedia

Jailbreak Detection

Jailbreak Detection is a security mechanism that identifies whether a mobile device has been unlocked from its manufacturer-imposed restrictions by monitoring for altered system states, unauthorized code execution, or the presence of known jailbreaking artifacts.

35

Publications

1.5K

Citations

100

Authors

21

Institutions

Publications per year

2017–2026

35

Parents

Publications

35

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Xinyue Shen, Zeyuan Chen, Michael Backes et al. · 2024 · 176 citations · Full text

, , +14

Automatic Prompt Optimization with “Gradient Descent” and Beam Search

Reid Pryzant, Dan Iter, Jerry Li et al. · 2023 · 148 citations · Full text

, , +14

Defending ChatGPT against jailbreak attack via self-reminders

Yueqi Xie, Jingwei Yi, Jiawei Shao et al. · Nature Machine Intelligence · 2023 · 117 citations

, , +7

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Yi Liu, Gelei Deng, Zhengzi Xu et al. · arXiv (Cornell University) · 2023 · 102 citations · Full text

, , +13

Jailbreaking Black Box Large Language Models in Twenty Queries

Patrick Chao, Alexander Robey, Edgar Dobriban et al. · 2025 · 94 citations

, , +13

1–5 of 35

Authors

100

  1. YL
    Yuekang Li

    Nanyang Technological University, Singapore

    3 publications · 211 citations

    4

    h-index

  2. GD
    Gelei Deng

    Nanyang Technological University, Singapore

    3 publications · 211 citations

    4

    h-index

  3. TZ
    Tianwei Zhang

    Nanyang Technological University, Singapore

    2 publications · 109 citations

    3

    h-index

  4. XS
    Xinyue Shen

    Chinese Academy of Agricultural Sciences, China

    2 publications · 219 citations

    3

    h-index

  5. FW
    Fangzhao Wu

    Tsinghua University, China

    1 publications · 117 citations

    3

    h-index

1–5 of 100

Institutions

21

  1. Nanyang Technological University

    Singapore, Singapore

    3 h-index

    5 publications

    460 citations

  2. University of Science and Technology of China

    Hefei, China

    3 h-index

    1 publications

    117 citations

  3. Huazhong University of Science and Technology

    Wuhan, China

    2 h-index

    5 publications

    276 citations

  4. Wuhan University

    Wuhan, China

    2 h-index

    2 publications

    66 citations

  5. Helmholtz Center for Information Security

    Saarbrücken, Germany

    2 h-index

    4 publications

    704 citations

  6. Tsinghua University

    Beijing, China

    2 h-index

    1 publications

    117 citations

  7. Microsoft Research Asia (China)

    Beijing, China

    2 h-index

    2 publications

    234 citations

  8. Hong Kong University of Science and Technology

    Hong Kong, Hong Kong

    2 h-index

    3 publications

    351 citations

1–8 of 21

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 359 citations

    10

    h-index

  2. SSRN Electronic Journal

    Repository · 1 publications · 14 citations

    1

    h-index

  3. Nature Machine Intelligence

    1 publications · 117 citations

    1

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 11 citations

  5. ACM Transactions on Software Engineering and Methodology

    TOSEM · 1 publications · 13 citations

1–5