AI-GAN: Attack-Inspired Generation of Adversarial Examples
Open accessAbstract
Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs. Recently different attacks and strategies have been proposed, but how to generate adversarial examples perceptually realistic and more efficiently remains unsolved. This paper proposes a novel framework called Attack-Inspired GAN (AI-GAN), where a generator, a discriminator, and an attacker are trained jointly. Once trained, it can generate adversarial perturbations efficiently given input images and target classes. Through extensive experiments on several popular datasets e.g., MNIST and CFAR-10, AI-GAN achieves high attack success rates and reduces generation time significantly in various settings. Moreover, for the first time, AI-GAN successfully scales to complicated datasets e.g., CFAR-100 with around 90% success rates among all classes.
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
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?
The black-box nature of AI can cause many security problems, which can come from internal or external sources.
“The black-box nature of AI can cause many security problems, which can come from internal or external sources.”
From Survey of Explainable AI Techniques in Healthcare (2023) · cites this paper as [13]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381 · see citing works
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · see citing works
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143 · see citing works
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244 · see citing works
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602 · see citing works
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375 · see citing works
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993 · see citing works
Conditional Image Synthesis With Auxiliary Classifier GANsPreprint
Odena, A., Olah, C., & Shlens, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09585 · Cited by 2,968 · see citing works
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176 · see citing works
Wide Residual NetworksPreprint
Zagoruyko, S., & Komodakis, N. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.07146 · Cited by 1,850 · see citing works
Chen, P., Zhang, H., Sharma, Y., Yi, J., & Hsieh, C. (2017) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/3128572.3140448 · Cited by 1,782 · see citing works
Generating Adversarial Examples with Adversarial Networks
Xiao, C., Li, B., Zhu, J.-Y., He, W., Liu, M., & Song, D. X. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/543 · Cited by 988 · see citing works
Self-citationDefense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative ModelsPreprint
Samangouei, P., Kabkab, M., & Chellappa, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06605 · Cited by 838 · see citing works
Generative Adversarial Perturbations
Poursaeed, O., Katsman, I., Gao, B., & Belongie, S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00465 · Cited by 370 · see citing works
Constructing Unrestricted Adversarial Examples with Generative ModelsPreprint
Song, Y., Shu, R., Kushman, N., & Ermon, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07894 · Cited by 227 · see citing works
Bag of Tricks for Adversarial TrainingPreprint
Pang, T., Yang, X. H., Dong, Y., Su, H., & Zhu, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00467 · Cited by 170 · see citing works
Self-citationRob-GAN: Generator, Discriminator, and Adversarial Attacker
Liu, X., & Hsieh, C. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.01149 · Cited by 129 · see citing works
AdvGAN++: Harnessing Latent Layers for Adversary Generation
Jandial, S., Mangla, P., Varshney, S., & Balasubramanian, V. N. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00257 · Cited by 91 · see citing works
Don't let your Discriminator be fooled.
Zhou, B., & Krähenbühl, P. (2018) · International Conference on Learning Representations · Cited by 20 · see citing works
GAP++: Learning to generate target-conditioned adversarial examplesPreprint
Mao, X., Chen, Y., Li, Y., He, Y., & Xue, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.05097 · Cited by 6 · see citing works
Flagged first, then by citations
3 of the 26 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio, "Generative Adversar- ial Nets," in NIPS, 2014, pp. 2672-2680.
- Pin-Yu Chen, Huan Zhang, Yash Sharma, Jinfeng Yi, and Cho-Jui Hsieh, "ZOO: Zeroth Order Optimiza- tion based Black-box Attacks to Deep Neural Networks without Training Substitute Models," in AISec, 2017, pp. 15-26.
Cited by
Sorted by citations
Survey of Explainable AI Techniques in Healthcare
Chaddad, A., Peng, J., Xu, J., & Bouridane, A. (2023) · Sensors · doi:10.3390/s23020634 · Cited by 591 · see citing works
Privacy and Security Concerns in Generative AI: A Comprehensive Survey
Golda, A., Mekonen, K. A., Pandey, A., Singh, A., Hassija, V., Chamola, V., & Sikdar, B. (2024) · IEEE Access · doi:10.1109/access.2024.3381611 · Cited by 269 · see citing works
Data Evaluation and Enhancement for Quality Improvement of Machine Learning
Chen, H., Chen, J., & Ding, J. (2021) · IEEE Transactions on Reliability · doi:10.1109/tr.2021.3070863 · Cited by 166 · see citing works
Self-citationFingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
Peng, Z., Li, S., Chen, G., Zhang, C., Zhu, H., & Xue, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01307 · Cited by 84 · see citing works
Exploring generative adversarial networks and adversarial training
Sajeeda, A., & Hossain, B. M. M. (2022) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2022.03.002 · Cited by 80 · see citing works
Liu, Z., & Yin, X. (2021) · IEEE Access · doi:10.1109/access.2021.3056482 · Cited by 43 · see citing works
A spatiotemporal graph transformer approach for Alzheimer’s disease diagnosis with rs-fMRI
He, P., Shi, Z., Cui, Y., Wang, R., & Wu, D. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108762 · Cited by 41 · see citing works
Investigating the practicality of adversarial evasion attacks on network intrusion detection
Merzouk, M. A., Cuppens, F., Cuppens-Boulahia, N., & Yaich, R. (2022) · Annals of Telecommunications · doi:10.1007/s12243-022-00910-1 · Cited by 38 · see citing works
Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks
Mozó, A., González-Prieto, Á., Pastor, A., Gómez-Canaval, S., & Talavera, E. (2022) · Scientific Reports · doi:10.1038/s41598-022-06057-2 · Cited by 33 · see citing works
Network intrusion detection based on multi-domain data and ensemble-bidirectional LSTM
Wang, X., Liu, J., & Zhang, C. (2023) · EURASIP Journal on Information Security · doi:10.1186/s13635-023-00139-y · Cited by 26 · see citing works
Targeted Universal Adversarial Examples for Remote Sensing
Bai, T., Wang, H., & Wen, B. (2022) · Remote Sensing · doi:10.3390/rs14225833 · Cited by 26 · see citing works
Self-citationAdversarial Machine Learning on Social Network: A Survey
Guo, S., Li, X., & Mu, Z. (2021) · Frontiers in Physics · doi:10.3389/fphy.2021.766540 · Cited by 17 · see citing works
Vax-a-Net: Training-Time Defence Against Adversarial Patch Attacks
Gittings, T., Schneider, S., & Collomosse, J. P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69538-5_15 · Cited by 15 · see citing works
Dual Attention Adversarial Attacks With Limited Perturbations
Duan, M., Qin, Y., Deng, J., Li, K., & Xiao, B. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3274142 · Cited by 13 · see citing works
Jia, E., Xu, Y., Zhang, Z., Zhang, F., Feng, W., Dong, L., Hui, T., & Tao, C. (2023) · Remote Sensing · doi:10.3390/rs15051439 · Cited by 12 · see citing works
A review of generative and non-generative adversarial attack on context-rich images
Stanly, H., Shalinie, S. M., & Paul, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106595 · Cited by 12 · see citing works
AdvEWM: Generating image adversarial examples by embedding digital watermarks
Xiang, Y., Li, T., Ren, W., He, J., Zhu, T., & Choo, K. R. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103662 · Cited by 11 · see citing works
Defense against adversarial examples based on wavelet domain analysis
Sarvar, A., & Amirmazlaghani, M. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03159-2 · Cited by 11 · see citing works
LIGAA: Generative adversarial attack method based on low-frequency information
Zhu, H., Zhu, Y., Zheng, H., Ren, Y., & Jiang, W. (2022) · Computers & Security · doi:10.1016/j.cose.2022.103057 · Cited by 10 · see citing works
Generating Universal Adversarial Perturbations for Quantum Classifiers
Anil, G., Vinod, V., & Narayan, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.28963 · Cited by 9 · see citing works
Governance Considerations of Adversarial Attacks on AI Systems
Lekota, N. (2024) · Proceedings of the International Conference on AI Research. · doi:10.34190/icair.4.1.3194 · Cited by 8 · see citing works
APDL: an adaptive step size method for white-box adversarial attacks
Hu, J., Li, X., Liu, C., Zhang, R., Tang, J., Sun, Y., & Wang, Y. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01748-x · Cited by 8 · see citing works
GEAAD: generating evasive adversarial attacks against android malware defense
Ahmad, N., Rana, A. S., Hadi, H. J., Hussain, F. B., Chakrabarti, P., Alshara, M. A., & Chakrabarti, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-96392-x · Cited by 8 · see citing works
Adversarial catoptric light: An effective, stealthy and robust physical-world attack to DNNs
Hu, C.-H., Shi, W.-W., Tian, L., & Li, W. (2022) · IET Computer Vision · doi:10.1049/cvi2.12264 · Cited by 7 · see citing works
An Adversarial sample defense method based on multi-scale GAN
Shao, M., Liu, S., Wang, R., & Zhang, G. (2021) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-021-01374-w · Cited by 7 · see citing works
HAG-NET: Hiding Data and Adversarial Attacking with Generative Adversarial Network
Fan, H., & Wang, J. (2024) · Entropy · doi:10.3390/e26030269 · Cited by 5 · see citing works
Using a GAN to Generate Adversarial Examples to Facial Image Recognition
Merrigan, A., & Smeaton, A. F. (2022) · Electronic Imaging · doi:10.2352/ei.2022.34.4.mwsf-210 · Cited by 5 · see citing works
Pavate, A. A., Bansode, R., Srinivasu, P. N., Shafi, J., Choi, J., & Ijaz, M. F. (2023) · IEEE Access · doi:10.1109/access.2023.3343754 · Cited by 5 · see citing works
Zhu, P., Jin, X., Jiang, Q., Gao, X., Wang, P., Yao, S., & Zhou, W. (2025) · Cybersecurity · doi:10.1186/s42400-024-00318-5 · Cited by 5 · see citing works
A Good Fishman Knows All the Angles: A Critical Evaluation of Google's Phishing Page Classifier
Miao, C., Feng, J., You, W., Shi, W., Huang, J., & Liang, B. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3623199 · Cited by 4 · see citing works
Gao, X., Lin, Q., Luo, C., Xie, W., Shen, L., Kusumam, K., & Song, S. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447287 · Cited by 3 · see citing works
Auwal, A. M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01154-8 · Cited by 2 · see citing works
The Role of AI Techniques in Diagnosing Health Conditions with Integration of AI
Viignesh, M. R., Selsia, A. J., Bhuvaneswari, M., Pathak, S., Yadav, K., & Amirthayogam, G. (2024) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite60783.2024.10617043 · Cited by 2 · see citing works
A single image deraining algorithm guided by text generation based on depth information conditions
Wei, X., Ye, X., Mei, X., Wang, J., & Ma, H. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113506 · Cited by 2 · see citing works
AdvFoolGen: Creating Persistent Troubles for Deep Classifiers
Ding, Y., Thakur, N., & Li, B. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00021 · Cited by 2 · see citing works
Self-citationVax-a-Net: Training-time Defence Against Adversarial Patch AttacksPreprint
Gittings, T., Schneider, S. A., & Collomosse, J. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.08194 · Cited by 2 · see citing works
Evading Detection Actively: Toward Anti-Forensics Against Forgery Localization
Zhuo, L., Luo, S., Tan, S., Chen, H., Li, B., & Huang, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3528062 · Cited by 1 · see citing works
Self-citationA universal framework for enhancing imperceptibility in latent diffusion-based adversarial attacks
Zhang, Y., Huang, D., & Zhang, H. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07433-1 · Cited by 1 · see citing works
An Adversarial Sample Defense Method Based on Saliency Information
Liu, S., Zhuang, Y., Ma, X., Wang, H., & Cao, D. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-0272-9_21 · Cited by 1 · see citing works
Attack Assessment and Augmented Identity Recognition for Human Skeleton Data
Zalameda, J. G., Witherow, M. A., Glandon, A., Aguilera, J. M., & Iftekharuddin, K. M. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191835 · Cited by 1 · see citing works
Evaluating Robustness of Reconstruction Models with Adversarial Networks
Sooksatra, K., Bejarano, G., & Rivas, P. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.08.174 · Cited by 1 · see citing works
A novel generalized adversarial image method using descriptive features
Hồ, T. P., Trung, P. D., & Bui, L. T. (2023) · Journal of Science and Technology on Information security · doi:10.54654/isj.v3i20.1002 · Cited by 1 · see citing works
Deep Generative Models as an Adversarial Attack Strategy for Tabular Machine Learning
Dyrmishi, S., Stoian, M. C., Giunchiglia, E., & Cordy, M. (2024) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc63072.2024.10935037 · Cited by 1 · see citing works
Generating corner cases for crashtesting deep networks
Platon, J., Avrin, G., & Chan-Hon-Tong, A. (2020) · HAL · Cited by 1 · see citing works
Generating Adaptive Targeted Adversarial Examples for Content-Based Image Retrieval
Pan, J., Zhu, X., & Liu, P. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892178 · Cited by 1 · see citing works
Research on adversarial attacks and defense
Xie, Y., Zhang, L., & Xiang, Y. (2022) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1117/12.2640997
Pham, D. T., Nguyen, C. T., Hồ, T. P., & Hải, N. N. (2023) · International Symposium on Information and Communication Technology · doi:10.1145/3628797.3628923
3D Convolution for Proactive Défense Against Localized Adversary Attacks
Ghebrechristos, H., & Alaghband, G. (2023) · International Conference on Soft Computing, Artificial Intelligence and Applications · doi:10.5121/csit.2023.132414
Immunizing Image Classifiers Against Localized Adversary Attack
Ghebrechristos, H., & Alaghband, G. (2024) · International Journal of Artificial Intelligence & Applications · doi:10.5121/ijaia.2024.15205
OSA-Diff: An Origin Sampling Based Adversarial Attack Using Diffusion Models
Jalalipour, S., & Rekabdar, B. (2025) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc64641.2025.00009
DBA: A Novel Diffusion-Based Method for Adversarial Defense via Image Restoration
Trung, P. D., Hồ, T. P., Khanh, D. D., & Hải, N. N. (2025) · International Conference on Cryptography and Information Security (VCRIS) · doi:10.1109/vcris68011.2025.11250547
Opportunities and Security Issues in Communication Engineering Using Generative AI
Charvi, Sharma, A., & Gulzar, Y. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9789815324693125040011
Text Adversarial Examples Attack and Defense Framework Based on Generative Adversarial Networks
Ma, S., Liu, P., Zhai, Y., Yu, M., Yang, W., & Zhang, J. (2025) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins68311.2025.11329875
173Chapter 10 GANs: applications and use cases
Abbasi, S., & Rahmani, A. M. (2025) · De Gruyter eBooks · doi:10.1515/9783111354934-010
Research on Image Adversarial Example Generation Method Based on Diff-AIGAN
Liu, H., Xu, J., & Liang, Y. (2025) · Industry science and engineering. · doi:10.62381/i255a06
Adversarial Example Generation Method Based on Wavelet Transform
Bi, M., Liang, X., Wang, B., Liu, L., Yin, X., & Liu, J. (2026) · Information · doi:10.3390/info17020182
GAN-Driven Defense for Securing Autonomous Vehicles from Emerging Cyber Threats
Khatun, M. A., Bhuiyan, M. S. M., Nava, E., Memon, S. F., Mukhtiar, N., Mohandas, R., & Dhirani, L. L. (2026) · Global Conference on Wireless and Optical Technologies (GCWOT) · doi:10.1109/gcwot69191.2026.11499711
Iqbal, K., Xue, Y., Rafique, A., Camacho, D., Ilyas, M., & Aurangzeb, K. (2026) · Expert Systems · doi:10.1111/exsy.70397
- Authors
- Bai, T., Zhao, J., Zhu, J., Han, S., Chen, J., Li, B., & Kot, A.
- Affiliations
- Nanyang Technological University (SG)
- University of Wisconsin–Madison (US)
- University of Illinois Urbana-Champaign (US)
- Venue
- 2021 IEEE International Conference on Image Processing (ICIP)
- Publisher
- IEEE
- Published
- 2021-09-19
- Pages
- 2543-2547
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W3005093931
- Cited by
- 58
- References
- 26
- Citations by year
- 2026: 4 · 2025: 12 · 2024: 10 · 2023: 14 · 2022: 10 · 2021: 6 · 2020: 2
- FWCI
- 4.62
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings - International Conference on Image Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- IEEE RESOURCE CENTERS
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- adversarial examples, adversarial perturbation generation, generative adversarial networks, deep neural network vulnerabilities, attack success rate
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
