The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
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
“Unfortunately, empirical evaluations indicate that even moderate transformations are sufficient to undermine the protective effectiveness of these methods 4 .”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024c
In the citing paper
“This presents a significant limitation, as image protectors are generally unable to ascertain the fine-tuning methodologies adopted by potential exploiters (Zhao et al., 2024c;Ren et al., 2024).”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024c
In the citing paper
“Zhao et al. (2024c) pointed out that, while such methods have demonstrated efficacy in controlled environments, their practical applicability remains limited.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024c
In the citing paper
“Moreover, their effectiveness varies considerably depending on the specific fine-tuning approach employed.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024c
In the citing paper
“Because these perturbations typically target the text encoder, they offer limited efficacy in cases where the learning process does not involve modifications to this component.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Zhao et al., 2024c
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
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
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2022) · arXiv · doi:10.48550/arxiv.2208.01618 · Cited by 611
Research works printed but not linked: 36
- Athalye, 2018, Synthesizing robust adversarial examples, 284
- 2022, “Art is dead Dude” - the rise of the AI artists stirs de-bate
- Carlini, (certified!!) adversarial robustness for free!
- 2022, AI won an art contest, and artists are furious
- Duan, 2023, Are diffusion models vulnerable to membership inference attacks?, 8717
- 10.1109/ICCV51070.2023.00230 · DOI
- Heusel, 2017, Gans trained by a two time-scale update rule converge to a local nash equilib-rium, Advances in neural information processing systems, 30
- 10.1145/3581783.3611833 · DOI
- Kang, 2023, Diffattack: Evasion attacks against diffusion-based adversarial purification
- Kong, 2023, An efficient membership inference attack for the diffusion model by proximal initialization, arXiv preprint
- 10.1109/CVPR52729.2023.00192 · DOI · Paper page
- Kynkäänniemi, 2019, Improved precision and recall met-ric for assessing generative models, Advances in Neural In-formation Processing Systems, 32
- 10.1109/ICCV51070.2023.00019 · DOI
- Liang, 2023, Adversarial example does good: Preventing painting imitation from diffusion models via adversarial examples, 20763
- Liu, 2024, Sora: A review on background, technology, limitations, and opportunities of large vision models, arXiv preprint
- 10.1109/ICCV.2015.425 · DOI · Paper page
- Meng, 2022, SDEdit: Guided image synthesis and editing with stochastic differential equations
- Nie, 2022, Diffusion models for adversarial purification, 16805
- Radiya-Dixit, 2022, Data poisoning wont save you from facial recognition
- 10.1109/CVPR52729.2023.02155 · DOI · Paper page
- Salman, 2023, Raising the cost of malicious ai-powered image editing, 29894
- Shan, 2023, Glaze: Protecting artists from style mimicry by Text-to-Image models, 2187
- Song, 2021, Denoising diffusion implicit models
- 10.1109/ICCV51070.2023.00202 · DOI
- Wang, 2022, Guided diffusion model for adversarial purification, arXiv preprint
- 10.1609/aaai.v37i2.25353 · DOI
- 2022, He made a childrens book using AI. Then came the rage
- 2016, Wikiart: Visual art encyclopedia
- Wu, 2023, Towards prompt-robust face privacy protection via adversarial decoupling augmentation framework, arXiv preprint
- Xue, 2023, Diffusion-based adversarial sample generation for improved stealthiness and controllability
- Ye, 2023, Duaw: Data-free universal adversarial watermark against stable diffusion customization, arXiv preprint
- Yoon, 2021, Adversar-ial purification with score-based generative models, 12062
- Yuan, 2023, Remind: Recov-ery of missing neuroimaging using diffusion models with application to alzheimers disease, medRxiv, 2023
- 10.1109/CVPR.2018.00068 · DOI · Paper page
- Zhao, 2023, Un-learnable examples for diffusion models: Protect data from unauthorized exploitation, arXiv preprint
- Zheng, 2023, Understanding and improving adversarial attacks on latent diffusion model, arXiv preprint
Cited by
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, Z., Duan, J., Xu, K., Wang, C., Zhang, R., Du, Z., Guo, Q., & Hu, X.
- Affiliations
- SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences
- Drexel University
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 24398-24407
- Cited by
- 25
- References
- 9
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
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.
