The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Silent Guardian: Protecting Text From Malicious Exploitation by Large Language Models
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
“Text Poisoning: Zhao et al. (2024a) proposed Truncation Protection Examples (TPEs).”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024a
In the citing paper
“These are specially manipulated texts designed to make the model to output the special final token, effectively stopping further generation.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024a
In the citing paper
“The experiments showed strong effectiveness in some areas, such as mathematics, where truncation efficacy reached 99%, but much weaker results in others, like coding, where effectiveness dropped to 22%.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024a
In the citing paper
“A different approach involves encoding the content into special Unicode characters, making it impossible for AI systems to process it (Zhao et al., 2024a).”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024a
In the citing paper
“A further limitation is that generating TPEs introduces manipulations into the protected text itself, which may make the text appear noisy or less readable to users.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024a
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · cited 1×
“The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks.”
BackgroundA Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254 · cited 1×
“R ECENT advances in large language models (LLMs) have led to impressive performance in a variety of downstream language tasks [1], such as holding natural conversation [2], text and code generation [3], [4], log anomaly detection [5] and reading comprehension [6].”
BackgroundQLoRA: Efficient Finetuning of Quantized LLMs
Dettmers, T., Pagnoni, A., Holtzman, A., & Zettlemoyer, L. (2023) · arXiv · doi:10.48550/arxiv.2305.14314 · Cited by 3,832
Cer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.11175 · Cited by 1,267
Universal and Transferable Adversarial Attacks on Aligned Language Models
Zou, A., Wang, Z., Carlini, N., Nasr, M., Kolter, J. Z., & Fredrikson, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15043 · Cited by 197
Neural Machine Translation with Byte-Level Subwords
Wang, C., Cho, K., & Gu, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6451 · Cited by 147
Research works printed but not linked: 40
- 10.1145/3581641.3584037 · DOI
- 10.1145/3581754.3584136 · DOI
- Ji, 2023, Log anomaly detection through GPT-2 for large scale systems, ZTE Commun., 21, 70
- Feng, 2023, Sentence simplification via large language models, arXiv:2302.11957 · arXiv
- Staab, 2023, Beyond memorization: Violating privacy via inference with large language models, arXiv:2310.07298 · arXiv
- 2023, Large Language Models and Plagiarism
- 10.1002/aaai.12188 · DOI · Paper page
- 10.1109/ACCESS.2019.2916674 · DOI
- 10.1609/aaai.v36i10.21415 · DOI
- Kirchenbauer, A watermark for large language models, 17061
- Qu, 2024, Provably robust multi-bit watermarking for AI-generated text via error correction code, arXiv:2401.16820 · arXiv
- Markwood, Mirage: Content masking attack against $information-based$ online services, 833
- 10.3390/app132413146 · DOI
- Wang, 2022, MPC-pipe: An efficient pipeline scheme for secure multi-party machine learning inference, arXiv:2209.13643 · arXiv
- Shen, $SOTER$: Guarding black-box inference for general neural networks at the edge, 723
- 10.3390/en15113959 · DOI
- 10.18653/v1/2020.emnlp-main.346 · DOI · Paper page
- 10.18653/v1/D19-1221 · DOI · Paper page
- 10.18653/v1/2021.emnlp-main.464 · DOI
- Wen, Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery, 1
- 10.14722/ndss.2019.23138 · DOI
- Ebrahimi, On adversarial examples for character-level neural machine translation, 653
- 10.18653/v1/2020.acl-main.540 · DOI
- 10.18653/v1/D18-1316 · DOI
- 10.18653/v1/2020.emnlp-main.500 · DOI
- Samanta, 2017, Towards crafting text adversarial samples, arXiv:1707.02812 · arXiv
- 10.18653/v1/N18-1170 · DOI
- Szegedy, Intriguing properties of neural networks, 1
- 10.1109/TSUSC.2023.3263510 · DOI
- 10.1145/3319535.3363201 · DOI
- Shetty, $A4NT$: Author attribute anonymity by adversarial training of neural machine translation, 1633
- 10.1137/1.9781611976700.24 · DOI
- Radford, Learning transferable visual models from natural language supervision, 8748
- Chiang, 2023, Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality
- Levenshtein, 1966, Binary codes capable of correcting deletions, insertions, and reversals, Proc. Sov. Phys. Doklady, 10, 707
- Deng, 2023, Jailbreaker: Automated jailbreak across multiple large language model chatbots, arXiv:2307.08715 · arXiv
- 2023, Tiktoken
- 10.18653/v1/D19-1670 · DOI
- Liu, 2023, Jailbreaking ChatGPT via prompt engineering: An empirical study, arXiv:2305.13860 · arXiv
- Jain, 2023, Baseline defenses for adversarial attacks against aligned language models, arXiv:2309.00614 · arXiv
Cited by
Understanding the effects of human-written paraphrases in LLM-generated text detection
Lau, H. T., & Zubiaga, A. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100151 · Cited by 13
Arnaudo, A., Coppola, R., Morisio, M., Vetrò, A., Borghi, M., Raso, R., & Khan, B. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3928 · Cited by 2
Metadata
- Authors
- Zhao, J., Chen, K., Yuan, X., Qi, Y., Zhang, W., & Yu, N.
- Affiliations
- CAS Key Laboratory of Electromagnetic Space Information, Anhui Province Key Laboratory of Digital Security, School of Information Science and Technology, University of Science and Technology of China, Hefei, China
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2024
- Volume
- 19
- Pages
- 8600-8615
- ISSN
- 1556-6013
- 1556-6021
- Cited by
- 12
- References
- 9
- Licence
- Funders
- National Natural Science Foundation of China (62121002, U20B2047, U2336206, 62102386, 62472398, 62372423)
- Open Foundation of Key Laboratory of Cyberspace Security, Ministry of Education (KLCS20240207)
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: Silent Guardian: Protecting Text From Malicious Exploitation by Large Language Models. https://app.cochat.ai/papers/10.1109/tifs.2024.3455775
- The paper
- Zhao, J., Chen, K., Yuan, X., Qi, Y., Zhang, W., & Yu, N. (2024). Silent Guardian: Protecting Text From Malicious Exploitation by Large Language Models. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2024.3455775
