{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:17:14Z","timestamp":1783577834646,"version":"3.55.0"},"reference-count":30,"publisher":"Korea Multimedia Society - English Version Journal","issue":"2","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466038"],"award-info":[{"award-number":["62466038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Provincial Key Laboratory of Image Processing and\n                                Pattern Recognition","award":["2024SSY03111"],"award-info":[{"award-number":["2024SSY03111"]}]},{"name":"Jiangxi Provincial Key Laboratory of Image Processing and\n                                Pattern Recognition","award":["ET202404437"],"award-info":[{"award-number":["ET202404437"]}]},{"DOI":"10.13039\/501100004479","name":"Jiangxi Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["20242BAB26015"],"award-info":[{"award-number":["20242BAB26015"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100009554","name":"Nanchang Hangkong University","doi-asserted-by":"publisher","award":["YC2024-S658"],"award-info":[{"award-number":["YC2024-S658"]}],"id":[{"id":"10.13039\/100009554","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.jmis.org"],"crossmark-restriction":true},"short-container-title":["J Multimed Inf Syst"],"DOI":"10.33851\/jmis.2026.13.2.73","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:42:02Z","timestamp":1783575722000},"page":"73-80","update-policy":"https:\/\/doi.org\/10.33851\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reversible Trigger Set for Copyright Protection of Neural\n                    Network"],"prefix":"10.33851","volume":"13","author":[{"given":"Kaiyang","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Leng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"19702","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"key2.0260709074153e+13_B1","doi-asserted-by":"crossref","unstructured":"M. Xue, Y. Zhang, J. Wang, and W. Liu, \u201cIntellectual property\n                    protection for deep learning models: Taxonomy, methods, attacks, and\n                    evaluations,\u201d IEEE Transactions on Artificial\n                        Intelligence, vol. 3, no. 6, pp. 908-923, 2021.","DOI":"10.1109\/TAI.2021.3133824"},{"key":"key2.0260709074153e+13_B2","doi-asserted-by":"crossref","unstructured":"T. Wang and K. Florian, \u201cAttacks on digital watermarks for\n                    deep neural networks,\u201d in IEEE International Conference on\n                        Acoustics, Speech and Signal Processing (ICASSP), 2019, pp.\n                    2622-2626.","DOI":"10.1109\/ICASSP.2019.8682202"},{"key":"key2.0260709074153e+13_B3","unstructured":"R. Tang, H. Jin, C. Wigington, M. Du, R. Jain, and X. Hu, Was My\n                    Model Stolen? Feature Sharing for Robust and Transferable Watermarks,\n                    2021."},{"key":"key2.0260709074153e+13_B4","doi-asserted-by":"crossref","unstructured":"Q. Feng, L. Leng, C. C. Chang, J. H. Horng, and M. Wu,\n                    \u201cReversible data hiding in encrypted images with extended parametric\n                    binary tree labeling,\u201d Applied Sciences, vol. 13, no. 4,\n                    p. 2458, 2023.","DOI":"10.3390\/app13042458"},{"key":"key2.0260709074153e+13_B5","doi-asserted-by":"crossref","unstructured":"Z. Q. Yang, T. Tang, H. Dang, Z. Wu, and E. C. Chang,\n                    \u201cEffectiveness of Distillation Attack and Countermeasure on Neural\n                    Network Watermarking,\u201d IEEE Transactions on Dependable and Secure\n                        Computing, 2025.","DOI":"10.1109\/TDSC.2025.3609476"},{"key":"key2.0260709074153e+13_B6","doi-asserted-by":"crossref","unstructured":"H. Kang, L. Leng, and C. C. Chang, \u201cOverlapped (7, 4) hamming\n                    code for large-capacity and low-loss data hiding,\u201d Multimedia\n                        Tools and Applications, vol. 82, no. 20, pp. 30345-30374,\n                    2023.","DOI":"10.1007\/s11042-023-14502-1"},{"key":"key2.0260709074153e+13_B7","doi-asserted-by":"crossref","unstructured":"S. Yang, L. Leng, C. C. Chang, and C. C. Chang, \u201cReversible\n                    adversarial examples with minimalist evolution for recognition control in\n                    computer vision,\u201d Applied Sciences, vol. 15, no. 3, p.\n                    1142, 2025.","DOI":"10.3390\/app15031142"},{"key":"key2.0260709074153e+13_B8","unstructured":"J. M. Barton, \u201cMethod and apparatus for embedding\n                    authentication information within digital data,\u201d U.S. Patent 5,646,997,\n                    Jul. 1997."},{"key":"key2.0260709074153e+13_B9","doi-asserted-by":"crossref","unstructured":"J. Tian, \u201cReversible data embedding using a difference\n                    expansion,\u201d IEEE Transactions on Circuits and Systems for Video\n                        Technology, vol. 13, no. 8, pp. 890-896, 2003.","DOI":"10.1109\/TCSVT.2003.815962"},{"key":"key2.0260709074153e+13_B10","doi-asserted-by":"crossref","unstructured":"P. C. Mandal, I. Mukherjee, and B. N. Chatterji, \u201cHigh\n                    capacity reversible and secured data hiding in images using interpolation and\n                    difference expansion technique,\u201d Multimedia Tools and\n                        Applications, vol. 80, no. 3, pp. 3623-3644, 2021.","DOI":"10.1007\/s11042-020-09341-3"},{"key":"key2.0260709074153e+13_B11","doi-asserted-by":"crossref","unstructured":"Z. Ni, Y. Q. Shi, N. Ansari, and W. Su, \u201cReversible data\n                    hiding,\u201d IEEE Transactions on Circuits and Systems for Video\n                        Technology, vol. 16, no. 3, pp. 354-362, 2006.","DOI":"10.1109\/TCSVT.2006.869964"},{"key":"key2.0260709074153e+13_B12","doi-asserted-by":"crossref","unstructured":"Y. Jia, Z. Yin, X. Zhang, and Y. Luo, \u201cReversible data hiding\n                    based on reducing invalid shifting of pixels in histogram shifting,\u201d\n                        Signal Processing, vol. 163, pp. 238-246,\n                    2019.","DOI":"10.1016\/j.sigpro.2019.05.020"},{"key":"key2.0260709074153e+13_B13","doi-asserted-by":"crossref","unstructured":"B. Padmaja and V. M. Manikandan, \u201cA novel prediction error\n                    histogram shifting-based reversible data hiding scheme for medical image\n                    transmission,\u201d in 2021 4th International Conference on Security\n                        and Privacy (ISEA-ISAP), 2021, pp. 1-6.","DOI":"10.1109\/ISEA-ISAP54304.2021.9688572"},{"key":"key2.0260709074153e+13_B14","doi-asserted-by":"crossref","unstructured":"C. Zhan, L. Leng, C. C. Chang, and J. H. Horng, \u201cReversible\n                    image fragile watermarking with dual tampering detection,\u201d\n                        Electronics, vol. 13, no. 10, p. 1884, May\n                    2024.","DOI":"10.3390\/electronics13101884"},{"key":"key2.0260709074153e+13_B15","doi-asserted-by":"crossref","unstructured":"Y. Uchida, Y. Nagai, S. Sakazawa, and S. Satoh, \u201cEmbedding\n                    watermarks into deep neural networks,\u201d in Proceedings of the 2017\n                        ACM International Conference on Multimedia Retrieval, 2017, pp.\n                    269-277.","DOI":"10.1145\/3078971.3078974"},{"key":"key2.0260709074153e+13_B16","unstructured":"L. Fan, K. W. Ng, and C. S. Chan, \u201cRethinking deep neural\n                    network ownership verification: Embedding passports to defeat ambiguity\n                    attacks,\u201d in Advances in Neural Information Processing Systems\n                        32, 2019."},{"key":"key2.0260709074153e+13_B17","unstructured":"Y. Adi, C. Baum, M. Cisse, B. Pinkas, and J. Keshet, \u201cTurning\n                    your weakness into a strength: Watermarking deep neural networks by\n                    backdooring,\u201d in 27th USENIX Security Symposium,\n                    Baltimore, MD, 2018, pp. 1615-1631."},{"key":"key2.0260709074153e+13_B18","unstructured":"J. Guo and M. Potkonjak, \u201cEvolutionary trigger set generation\n                    for DNN black-box watermarking,\u201d arXiv Prep.\n                        arXiv:1906.04411, 2019."},{"key":"key2.0260709074153e+13_B19","doi-asserted-by":"crossref","unstructured":"J. Jia, B. Wang, and N. Z. Gong, \u201cRobust and verifiable\n                    information embedding attacks to deep neural networks via error-correcting\n                    codes,\u201d in Proceedings of the 2021 ACM Asia Conference on\n                        Computer and Communications Security, 2021, pp.\n                    2-13.","DOI":"10.1145\/3433210.3437519"},{"key":"key2.0260709074153e+13_B20","unstructured":"H. Jia, C. A. Choquette-Choo, V. Chandrasekaran, and N. Papernot,\n                    \u201cEntangled watermarks as a defense against model extraction,\u201d in\n                        30th USENIX Security Symposium, Virtual, 2021, pp.\n                    1937-1954."},{"key":"key2.0260709074153e+13_B21","doi-asserted-by":"crossref","unstructured":"T. Gu, K. Liu, B. Dolan-Gavitt, and S. Garg, \u201cBadNets:\n                    Evaluating backdooring attacks on deep neural networks,\u201d IEEE\n                        Access, vol. 7, pp. 47230-47244, 2019.","DOI":"10.1109\/ACCESS.2019.2909068"},{"key":"key2.0260709074153e+13_B22","unstructured":"X. Chen, C. Liu, B. Li, K. Lu, and D. Song, \u201cTargeted\n                    backdoor attacks on deep learning systems using data poisoning,\u201d\n                        arXiv Prep. arXiv:1712.05526, 2017."},{"key":"key2.0260709074153e+13_B23","doi-asserted-by":"crossref","unstructured":"E. Le Merrer, P. Perez, and G. Tr\u00e9dan, \u201cAdversarial\n                    frontier stitching for remote neural network watermarking,\u201d\n                        Neural Computing and Applications, vol. 32, no. 13, pp.\n                    9233-9244, 2020.","DOI":"10.1007\/s00521-019-04434-z"},{"key":"key2.0260709074153e+13_B24","doi-asserted-by":"crossref","unstructured":"Q. Zhong, L. Y. Zhang, J. Zhang, L. Gao, and Y. Xiang,\n                    \u201cProtecting IP of deep neural networks with watermarking: A new label\n                    helps,\u201d in Pacific-Asia Conference on Knowledge Discovery and\n                        Data Mining (PAKDD), Sydney, Australia, 2020, pp.\n                    462-474.","DOI":"10.1007\/978-3-030-47436-2_35"},{"key":"key2.0260709074153e+13_B25","doi-asserted-by":"crossref","unstructured":"N. Chattopadhyay and A. Chattopadhyay, \u201cRowback: Robust\n                    watermarking for neural networks using backdoors,\u201d in 20th IEEE\n                        International Conference on Machine Learning and Applications,\n                    2021, pp. 1728-1735.","DOI":"10.1109\/ICMLA52953.2021.00274"},{"key":"key2.0260709074153e+13_B26","doi-asserted-by":"crossref","unstructured":"B. Wang, F. Yu, F. Wei, Y. Li, and W. Wang, \u201cInvisible\n                    intruders: Label-consistent backdoor attack using re-parameterized noise\n                    trigger,\u201d IEEE Transactions on Multimedia, vol. 26, pp.\n                    10766-10778, 2024.","DOI":"10.1109\/TMM.2024.3412388"},{"key":"key2.0260709074153e+13_B27","unstructured":"A. Turner, D. Tsipras, and A. Madry, \u201cLabel-consistent\n                    backdoor attacks,\u201d arXiv Prep. arXiv:1912.02771,\n                    2019."},{"key":"key2.0260709074153e+13_B28","doi-asserted-by":"crossref","unstructured":"M. Barni, K. Kassem, and B. Tondi, \u201cA new backdoor attack in\n                    CNNs by training set corruption without label poisoning,\u201d in IEEE\n                        International Conference on Image Processing (ICIP), Taipei,\n                    Taiwan, 2019, pp.101-105.","DOI":"10.1109\/ICIP.2019.8802997"},{"key":"key2.0260709074153e+13_B29","doi-asserted-by":"crossref","unstructured":"J. Zhang, C. Dongdong, Q. Huang, and J. Liao, \u201cPoison ink:\n                    Robust and invisible backdoor attack,\u201d IEEE Transactions on Image\n                        Processing, vol. 31, pp. 5691-5705, 2022.","DOI":"10.1109\/TIP.2022.3201472"},{"key":"key2.0260709074153e+13_B30","unstructured":"A. Bansal, P. Chiang, M. J. Curry, R. Jain, C. Wigington, and V.\n                    Manjunatha, et al., \u201cCertified neural network watermarks with randomized\n                    smoothing,\u201d in International Conference on Machine\n                        Learning, Baltimore, MD, 2022, pp. 1450-1465."}],"container-title":["Journal of Multimedia Information System"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.jmis.org\/download\/download_pdf?doi=10.33851\/JMIS.2026.13.2.73","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.jmis.org\/download\/download_pdf?doi=10.33851\/JMIS.2026.13.2.73","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:42:14Z","timestamp":1783575734000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.jmis.org\/archive\/view_article?doi=10.33851\/JMIS.2026.13.2.73"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.33851\/JMIS.2026.13.2.73"],"URL":"https:\/\/doi.org\/10.33851\/jmis.2026.13.2.73","relation":{},"ISSN":["2383-7632"],"issn-type":[{"value":"2383-7632","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2026-02-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}