{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T21:43:32Z","timestamp":1788126212015,"version":"build-2803163510"},"reference-count":42,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T00:00:00Z","timestamp":1651276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62072127"],"award-info":[{"award-number":["62072127"]}]},{"name":"National Natural Science Foundation of China","award":["62002076"],"award-info":[{"award-number":["62002076"]}]},{"name":"National Natural Science Foundation of China","award":["202002030131"],"award-info":[{"award-number":["202002030131"]}]},{"name":"National Natural Science Foundation of China","award":["201904010493"],"award-info":[{"award-number":["201904010493"]}]},{"name":"National Natural Science Foundation of China","award":["2019A1515110213"],"award-info":[{"award-number":["2019A1515110213"]}]},{"name":"National Natural Science Foundation of China","award":["2020A1515010423"],"award-info":[{"award-number":["2020A1515010423"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["62072127"],"award-info":[{"award-number":["62072127"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["62002076"],"award-info":[{"award-number":["62002076"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["202002030131"],"award-info":[{"award-number":["202002030131"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["201904010493"],"award-info":[{"award-number":["201904010493"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["2019A1515110213"],"award-info":[{"award-number":["2019A1515110213"]}]},{"name":"CNKLSTISS, Science and Technology Program of Guangzhou, China","award":["2020A1515010423"],"award-info":[{"award-number":["2020A1515010423"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["62072127"],"award-info":[{"award-number":["62072127"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["62002076"],"award-info":[{"award-number":["62002076"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["202002030131"],"award-info":[{"award-number":["202002030131"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["201904010493"],"award-info":[{"award-number":["201904010493"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["2019A1515110213"],"award-info":[{"award-number":["2019A1515110213"]}]},{"name":"Guangdong basic and applied basic research fund joint fund Youth Fund","award":["2020A1515010423"],"award-info":[{"award-number":["2020A1515010423"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["62072127"],"award-info":[{"award-number":["62072127"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["62002076"],"award-info":[{"award-number":["62002076"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["202002030131"],"award-info":[{"award-number":["202002030131"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["201904010493"],"award-info":[{"award-number":["201904010493"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["2019A1515110213"],"award-info":[{"award-number":["2019A1515110213"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["2020A1515010423"],"award-info":[{"award-number":["2020A1515010423"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable to adversarial examples that make the model\u2019s predictions wrong due to some specific subtle perturbation, and these technologies can be abused for the tampering with and forgery of multimedia, i.e., deep forgery. In this paper, we propose a universal detection framework for adversarial examples and fake images. We observe some differences in the distribution of model outputs for normal and adversarial examples (fake images) and train the detector to learn the differences. We perform extensive experiments on the CIFAR10 and CIFAR100 datasets. Experimental results show that the proposed framework has good feasibility and effectiveness in detecting adversarial examples or fake images. Moreover, the proposed framework has good generalizability for the different datasets and model structures.<\/jats:p>","DOI":"10.3390\/s22093445","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T08:26:35Z","timestamp":1651566395000},"page":"3445","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Universal Detection Method for Adversarial Examples and Fake Images"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2095-4875","authenticated-orcid":false,"given":"Jiewei","family":"Lai","sequence":"first","affiliation":[{"name":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China"},{"name":"Pazhou Lab, Guangzhou 510330, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-6470","authenticated-orcid":false,"given":"Yantong","family":"Huo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3734-7350","authenticated-orcid":false,"given":"Ruitao","family":"Hou","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3480-8780","authenticated-orcid":false,"given":"Xianmin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Bengio","year":"2015","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3087","DOI":"10.1002\/int.22397","article-title":"Enhancing intrusion detection with feature selection and neural network","volume":"36","author":"Wu","year":"2021","journal-title":"Int. J. Intell. Syst."},{"key":"ref_3","unstructured":"Wang, X., Liang, Z., Koe, A.S.V., Wu, Q., Zhang, X., Li, H., and Yang, Q. (2021). Secure and efficient parameters aggregation protocol for federated incremental learning and its applications. Int. J. Intell. Syst., 1\u201317."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5770","DOI":"10.1002\/int.22529","article-title":"Hybrid sequence-based Android malware detection using natural language processing","volume":"36","author":"Zhang","year":"2021","journal-title":"Int. J. Intell. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1002\/int.22330","article-title":"Analyzing host security using D-S evidence theory and multisource information fusion","volume":"36","author":"Li","year":"2021","journal-title":"Int. J. Intell. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jpdc.2019.03.003","article-title":"The security of machine learning in an adversarial setting: A survey","volume":"130","author":"Wang","year":"2019","journal-title":"J. Parallel Distrib. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mo, K., Tang, W., Li, J., and Yuan, X. (2022). Attacking Deep Reinforcement Learning with Decoupled Adversarial Policy. IEEE Trans. Dependable Secur. Comput.","DOI":"10.1109\/TDSC.2022.3143566"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/j.ins.2020.09.064","article-title":"PPCL: Privacy-preserving collaborative learning for mitigating indirect information leakage","volume":"548","author":"Yan","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1002\/int.22315","article-title":"Querying little is enough: Model inversion attack via latent information","volume":"36","author":"Mo","year":"2021","journal-title":"Int. J. Intell. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3325","DOI":"10.1007\/s13042-020-01242-z","article-title":"Adversarial examples: Attacks and defenses in the physical world","volume":"12","author":"Ren","year":"2021","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rao, Y., and Ni, J. (2021, January 11\u201317). Self-Supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01476"},{"key":"ref_12","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv."},{"key":"ref_13","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Carlini, N., and Wagner, D. (2017, January 22\u201326). Towards evaluating the robustness of neural networks. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2017.49"},{"key":"ref_15","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (July, January 26). Deepfool: A simple and accurate method to fool deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Guo, S., Geng, S., Xiang, T., Liu, H., and Hou, R. (2021). ELAA: An efficient local adversarial attack using model interpreters. Int. J. Intell. Syst., 1\u201323.","DOI":"10.1002\/int.22680"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3295","DOI":"10.1007\/s13042-020-01240-1","article-title":"Generating transferable adversarial examples based on perceptually-aligned perturbation","volume":"12","author":"Chen","year":"2021","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.ins.2020.03.066","article-title":"Adversarial attacks on deep-learning-based radar range profile target recognition","volume":"531","author":"Huang","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102632","DOI":"10.1016\/j.jnca.2020.102632","article-title":"Adversarial attacks on deep-learning-based SAR image target recognition","volume":"162","author":"Huang","year":"2020","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1002\/int.22349","article-title":"Camdar-adv: Generating adversarial patches on 3D object","volume":"36","author":"Chen","year":"2021","journal-title":"Int. J. Intell. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017, January 22\u201326). Membership inference attacks against machine learning models. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2017.41"},{"key":"ref_22","unstructured":"Li, Y., Tang, T., Hsieh, C.J., and Lee, T. (2021). Detecting Adversarial Examples with Bayesian Neural Network. arXiv."},{"key":"ref_23","unstructured":"Kurakin, A., Goodfellow, I., and Bengio, S. (2016). Adversarial examples in the physical world. arXiv."},{"key":"ref_24","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2017). Towards deep learning models resistant to adversarial attacks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., and Frossard, P. (2017, January 21\u201326). Universal adversarial perturbations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref_26","unstructured":"Feinman, R., Curtin, R.R., Shintre, S., and Gardner, A.B. (2017). Detecting adversarial samples from artifacts. arXiv."},{"key":"ref_27","unstructured":"Ma, X., Li, B., Wang, Y., Erfani, S.M., Wijewickrema, S., Schoenebeck, G., Song, D., Houle, M.E., and Bailey, J. (2018). Characterizing adversarial subspaces using local intrinsic dimensionality. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Tian, S., Yang, G., and Cai, Y. (2018, January 2\u20137). Detecting adversarial examples through image transformation. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11828"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Meng, D., and Chen, H. (November, January 30). Magnet: A two-pronged defense against adversarial examples. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.","DOI":"10.1145\/3133956.3134057"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lu, J., Issaranon, T., and Forsyth, D. (2017, January 22\u201329). Safetynet: Detecting and rejecting adversarial examples robustly. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.56"},{"key":"ref_31","first-page":"100004","article-title":"Generative adversarial network: An overview of theory and applications","volume":"1","author":"Aggarwal","year":"2021","journal-title":"Int. J. Inf. Manag. Data Insights"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1109\/TIFS.2020.3025438","article-title":"An automatic cost learning framework for image steganography using deep reinforcement learning","volume":"16","author":"Tang","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/TIFS.2017.2656823","article-title":"Image forgery localization via integrating tampering possibility maps","volume":"12","author":"Li","year":"2017","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Qiu, X., Li, H., Luo, W., and Huang, J. (2014, January 14). A universal image forensic strategy based on steganalytic model. Proceedings of the 2nd ACM Workshop on Information Hiding and Multimedia Security, New York, NY, USA.","DOI":"10.1145\/2600918.2600941"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Marra, F., Gragnaniello, D., Cozzolino, D., and Verdoliva, L. (2018, January 10\u201312). Detection of gan-generated fake images over social networks. Proceedings of the 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Miami, FL, USA.","DOI":"10.1109\/MIPR.2018.00084"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"532-1","DOI":"10.2352\/ISSN.2470-1173.2019.5.MWSF-532","article-title":"Detecting GAN generated fake images using co-occurrence matrices","volume":"2019","author":"Nataraj","year":"2019","journal-title":"Electron. Imaging"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Dang, H., Liu, F., Stehouwer, J., Liu, X., and Jain, A.K. (2020, January 14\u201319). On the detection of digital face manipulation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhang, X., Karaman, S., and Chang, S.F. (2019, January 9\u201312). Detecting and simulating artifacts in gan fake images. Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security (WIFS), Delft, The Netherlands.","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Wang, O., Zhang, R., Owens, A., and Efros, A.A. (2020, January 14\u201319). CNN-generated images are surprisingly easy to spot\u2026 for now. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref_40","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia."},{"key":"ref_41","unstructured":"Gong, X., Chang, S., Jiang, Y., and Wang, Z. (November, January 27). Autogan: Neural architecture search for generative adversarial networks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_42","unstructured":"Jiang, Y., Chang, S., and Wang, Z. (2021, January 6\u201314). Transgan: Two pure transformers can make one strong gan, and that can scale up. Proceedings of the Advances in Neural Information Processing Systems 34 (NeurIPS 2021), Virtual."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3445\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:05:08Z","timestamp":1760137508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,30]]},"references-count":42,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["s22093445"],"URL":"https:\/\/doi.org\/10.3390\/s22093445","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,30]]}}}