Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent
The DOI matches its Crossref record; 2 of the 2 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
“We choose it because the embedded payload is visually indistinguishable from legitimate content, unlike white-on-white text or zero-width Unicode characters, making it harder to detect and more representative of real-world attacks.”
From LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers (2026) · cites this paper as Zhang et al., 2026
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
CARER: Contextualized Affect Representations for Emotion Recognition
Saravia, E., Liu, H.-C. T., Huang, Y.-H., Wu, J., & Chen, Y.-S. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1404 · Cited by 698
Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
Gao, J., Lanchantin, J., Soffa, M. L., & Qi, Y. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00016 · Cited by 693
Research works printed but not linked: 28
- 10.5860/lrts.44n3.160 · doi:10.5860/lrts.44n3.160
- 10.1177/0894439320909085 · DOI
- 10.1177/17504813211002038 · DOI
- 10.1007/978-3-031-25069-9_24 · DOI
- 10.18653/v1/2022.naacl-main.339 · DOI · Paper page
- Formento, Confidence elicitation: A new attack vector for large language models
- Belinkov, Synthetic and natural noise both break neural machine translation
- 10.14722/ndss.2019.23138 · DOI · Paper page
- 10.1609/aaai.v34i05.6311 · DOI · Paper page
- 10.18653/v1/2021.emnlp-main.117 · DOI · Paper page
- 10.18653/v1/2022.naacl-main.43 · DOI
- 10.18653/v1/2020.emnlp-demos.16 · DOI · Paper page
- 10.18653/v1/2021.acl-short.43 · DOI
- 10.18653/v1/2021.eacl-main.88 · DOI
- 10.18653/v1/2024.eacl-long.125 · doi:10.18653/v1/2024.eacl-long.125
- Liu, Attribot: A bag of tricks for efficiently approximating leave-one-out context attribution
- 10.18653/v1/D19-1410 · DOI · Paper page
- 10.18653/v1/2020.emnlp-main.500 · DOI · Paper page
- 10.1109/BigData62323.2024.10825615 · DOI
- 10.18653/v1/D13-1170 · DOI · Paper page
- 10.18653/v1/2020.acl-main.148 · DOI · Paper page
- Sanh, 2019, Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter, ArXiv
- Liu, 2019, Roberta: A robustly optimized BERT pretraining approach, CoRR
- 10.1007/s10579-023-09704-w · DOI
- 10.18653/v1/2025.acl-long.684 · DOI
- Liu, Hqa-attack: Toward high quality black-box hard-label adversarial attack on text
- 10.1609/aaai.v38i17.29950 · DOI
- Rocamora, Revisiting character-level adversarial attacks for language models
Cited by
Li, L., Xiong, J., Zhu, C., Yu, R., Chen, C., Wang, J., Ma, R., & Lu, Z. (2026) · arXiv · doi:10.48550/arxiv.2605.25415 · Cited by 9
Metadata
- Authors
- Zhang, Y., Wang, X., Liu, J., Wang, W., Ma, Z., & Jia, X.
- Affiliations
- Lanzhou University
- Peking University
- Sun Yat-sen University
- Venue
- ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2026-05-03
- Pages
- 13647-13651
- Cited by
- 0
- References
- 2
- Funders
- National Natural Science Foundation of China
- Research and Development
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: Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent. https://app.cochat.ai/papers/10.1109/icassp55912.2026.11463036
- The paper
- Zhang, Y., Wang, X., Liu, J., Wang, W., Ma, Z., & Jia, X. (2026). Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent. ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp55912.2026.11463036
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.