The DOI matches its Crossref record.
Robust Jailbreak Detection in Large Language Models Using Behavioral Fingerprinting
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The structured-output and post-processing safeguards also reduce the risk of instruction leakage from user-generated text, but they are not equivalent to a full jailbreak or prompt-injection audit [22].”
From El Niño Discourse and the Limits of Single-Platform Inference (2026) · cites this paper as [22]
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
No references could be resolved yet.
Research works printed but not linked: 15
- Hu, 2024, Gradient cuff: Detecting jailbreak attacks on large language models by exploring refusal loss landscapes, arXiv preprint
- Galinkin, 2024, Improved Large Language Model Jailbreak Detection via Pretrained Embeddings, arXiv preprint
- Wang, 2025, STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models, arXiv preprint
- Mu, 2024, Stealthy jailbreak attacks on large language models via benign data mirroring, arXiv preprint
- 10.1093/comjnl/bxae124 · DOI
- Zhu, 2025, Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test, arXiv preprint
- Yamabe, 2024, MergePrint: Robust Fingerprinting against Merging Large Language Models, arXiv preprint
- Zhang, 2025, JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation, arXiv preprint
- Chao, 2024, Jailbreakbench: An open robustness benchmark for jailbreaking large language models, arXiv preprint
- 10.18653/v1/2025.naacl-long.623 · DOI
- Sharma, 2025, Constitutional classifiers: Defending against universal jailbreaks across thousands of hours of red teaming, arXiv preprint
- Nian, 2025, JailDAM: Jailbreak Detection with Adaptive Memory for VisionLanguage Model, arXiv preprint
- Shen, 2024, Jailbreak antidote: Runtime safety-utility balance via sparse representation adjustment in large language models, arXiv preprint
- Yenugula, 2024, Challenges With Accountability, Trust & System Security in Google Cloud Platform (GCP)
- Gore, 2023, Brain tumour segmentation and analysis using BraTS dataset with the help of an improvised 2D and 3D UNet model, 10.21203/rs.3.rs-2791706/v1 · DOI
Cited by
El Niño Discourse and the Limits of Single-Platform Inference
Erokhin, D., & Komendantova, N. (2026) · Information · doi:10.3390/info17070622 · Cited by 1
Metadata
- Authors
- Tumma, C., Reddy, R. A., Yadav, R., Salati, A., S, S., & A, K.
- Venue
- 2025 International Conference on Modeling, Simulation & Intelligent Computing (MoSICom)
- Publisher
- IEEE
- Published
- 2025-12-10
- Pages
- 284-289
- Cited by
- 4
- References
- 0
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: Robust Jailbreak Detection in Large Language Models Using Behavioral Fingerprinting. https://app.cochat.ai/papers/10.1109/mosicom67153.2025.11398297
- The paper
- Tumma, C., Reddy, R. A., Yadav, R., Salati, A., S, S., & A, K. (2025). Robust Jailbreak Detection in Large Language Models Using Behavioral Fingerprinting. 2025 International Conference on Modeling, Simulation & Intelligent Computing (MoSICom). https://doi.org/10.1109/mosicom67153.2025.11398297
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.