Attention Tracker: Detecting Prompt Injection Attacks in LLMs
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
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.
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
“Attention Tracker detects prompt injection by analyzing LLM attention mechanisms: attacks create characteristic distraction effects where attention scores shift from instructions to injected content [34].”
From Prompt Injection Attacks in Large Language Models and AI Agent Systems: A Comprehensive Review of Vulnerabilities, Attack Vectors, and Defense Mechanisms (2026) · cites this paper as [34]
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
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team, Riviere, M., Pathak, S., Sessa, P. G., Hardin, C., Bhupatiraju, S., Hussenot, L., Mesnard, T., Shahriari, B., Ramé, A., et al. (2024) · arXiv · doi:10.48550/arxiv.2408.00118 · Cited by 149
Ignore Previous Prompt: Attack Techniques For Language Models
Perez, F., & Ribeiro, I. (2022) · arXiv · doi:10.48550/arxiv.2211.09527 · Cited by 110
Optimization-based Prompt Injection Attack to LLM-as-a-Judge
Shi, J., Yuan, Z., Liu, Y., Huang, Y., Zhou, P., Sun, L., & Gong, N. Z. (2024) · Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3658644.3690291 · Cited by 70
Rethinking Interpretability in the Era of Large Language Models
Singh, C., Inala, J. P., Galley, M., Caruana, R., & Gao, J. (2024) · arXiv · doi:10.48550/arxiv.2402.01761 · Cited by 50
Hidden Trigger Backdoor Attacks
Saha, A., Subramanya, A., & Pirsiavash, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6871 · Cited by 13
Defending Against Indirect Prompt Injection Attacks With Spotlighting
Hines, K., Lopez, G., Hall, M., Zarfati, F., Zunger, Y., & Kiciman, E. (2024) · arXiv · doi:10.48550/arxiv.2403.14720 · Cited by 8
Cited by
Gulyamov, S., Gulyamov, S., Rodionov, A., Khursanov, R., Mekhmonov, K., Babaev, D., & Rakhimjonov, A. (2026) · Information · doi:10.3390/info17010054 · Cited by 45
ModelShield: Adaptive and Robust Watermark Against Model Extraction Attack
Pang, K., Qi, T., Wu, C., Bai, M., Jiang, M., & Huang, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3530691 · Cited by 29
A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
Su, H., Luo, J., Liu, C., Yang, X., Zhang, Y., Dong, Y., & Zhu, J. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3688650 · Cited by 11
Instruction Following by Principled Boosting Attention of Large Language Models
Guardieiro, V., Khare, A., Stein, A., & Wong, E. (2025) · arXiv · doi:10.48550/arxiv.2506.13734
Metadata
- Authors
- Hung, K.-H., Ko, C.-Y., Rawat, A., Chung, I.-H., Hsu, W. H., & Chen, P.-Y.
- Venue
- Findings of the Association for Computational Linguistics: NAACL 2025
- Published
- 2025
- Pages
- 2309-2322
- Cited by
- 34
- References
- 7
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: Attention Tracker: Detecting Prompt Injection Attacks in LLMs. https://app.cochat.ai/papers/10.18653/v1/2025.findings-naacl.123
- The paper
- Hung, K.-H., Ko, C.-Y., Rawat, A., Chung, I.-H., Hsu, W. H., & Chen, P.-Y. (2025). Attention Tracker: Detecting Prompt Injection Attacks in LLMs. Findings of the Association for Computational Linguistics: NAACL 2025. https://doi.org/10.18653/v1/2025.findings-naacl.123
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.