信息保密與信息隱藏:將敏感信息或文件隱藏在一副圖像、一段音樂或視頻中,起到信息保密的作用。輸入密碼,還可從含密圖像、音樂或視頻中完整提取出原始敏感信息或文件。這種信息保密方法與傳統(tǒng)加密方法不同,可使秘密信息或文件“徹底消失”,從而察覺不到秘密信息的存在性。
版權(quán)保護、防偽溯源與數(shù)字水印:一些正規(guī)商家辛辛苦苦拍攝的商品圖片和視頻,卻被山寨店鋪輕松利用并進行宣傳,這不僅會對圖像和視頻的原創(chuàng)者帶來損失,也會對消費者誤導(dǎo)。非授權(quán)、AI生成或篡改的非法圖片和視頻在社交網(wǎng)絡(luò)傳播和擴散,會對個人和社會造成不良影響,破壞正常的社會秩序,因此需要追究其責(zé)任。解決這些問題的一種重要技術(shù)就是在圖片和視頻中添加魯棒水印進行版權(quán)保護和溯源,且不影響其視覺質(zhì)量和使用價值。
人工智能(AI)與數(shù)字取證:眼見一定為實、耳聽一定為真嗎?答案是“No!”。大模型時代的到來,使得圖像、音視頻等多媒體信息的生成、編輯和篡改愈發(fā)容易,因此偽造或AIGC圖片、聲音、視頻難以辨認。通過結(jié)合機器學(xué)習(xí)、深度學(xué)習(xí)、大模型等人工智能方法,可實現(xiàn)對質(zhì)疑的多媒體信息鑒別真?zhèn)?,以AI攻AI,使AI向善向美。
魯棒哈希與生物認證:防欺騙性高的身份信息可以是生物指紋、聲紋、人臉等生物特征,這些生物特征具有一定的感知冗余。感知哈希具有魯棒性、抗碰撞性、緊湊性和安全性等特點,通過生成這些生物特征的魯棒哈希,可達到基于生物特征身份認證的目的。
主持的主要科研項目
1.國家自然科學(xué)基金-面上,面向分享平臺的自適應(yīng)魯棒視頻水印研究,62272331,2023.1-2026.12
2.國家自然科學(xué)基金-面上,基于人工免疫系統(tǒng)的信息隱藏研究,61972269,2020.1-2023.12
3.國家自然科學(xué)基金-聯(lián)合,保持碼率的高容量壓縮域視頻信息隱藏研究,U1536110,2016.1-2018.12
4.國家自然科學(xué)基金-面上,數(shù)字語音真實性的主動取證及其安全性研究,61170226,2012.1-2015.12
5.國家自然科學(xué)基金-青年,基于內(nèi)容的自適應(yīng)音頻水印研究,60702025,2008.1-2010.12
6.四川省科技計劃(重點研發(fā)項目),社交網(wǎng)絡(luò)虛假媒體內(nèi)容智能檢測技術(shù)研究,2022YFG0320,2022.1-2023.12
7.河南省網(wǎng)絡(luò)空間態(tài)勢感知重點實驗室開放課題(重點項目),載體源失配條件下自適應(yīng)隱寫的智能檢測技術(shù)研究,HNTS2022003,2022.5-2024.4
8.企業(yè)產(chǎn)學(xué)研項目,數(shù)字內(nèi)容溯源水印技術(shù)研究,24H0831,2024.6-2026.12
9.企業(yè)產(chǎn)學(xué)研項目,魯棒性視頻水印技術(shù)研究,21H0093,2021.1-2021.12
10.企業(yè)產(chǎn)學(xué)研項目,文檔與圖像水印技術(shù)研究,22H0517,2022.6-2023.5
11.企業(yè)產(chǎn)學(xué)研項目,原生溯源研究,21H0793,2021.6-2021.12
12.企業(yè)產(chǎn)學(xué)研項目,音頻篡改發(fā)現(xiàn)研究,21H0792,2021.6-2021.12
13.教育部博士點基金(博導(dǎo)類),混沌脆弱水印技術(shù)研究,20070613024,2008.1-2010.12
14.四川省青年科技基金(四川省杰出青年學(xué)科帶頭人資助計劃),基于人類心理聲學(xué)模型的壓縮域音頻水印研究,07ZQ026-004,2007.6-2011.6
15.成都市科技計劃,壓縮域視頻信息隱藏技術(shù)研究,12DXYB214JH-002,2013.1-2014.12
16. 中國博士后科學(xué)基金,混沌信息隱藏技術(shù)在圖像認證中的應(yīng)用研究,2003033304,2003.6-2004.6
近幾年代表性論文
1.Y. Chen,H. Wang, W. Li, W. Li, “A steganography immunoprocessing framework against CNN-based and handcrafted steganalysis,” IEEE Transactions on Information Forensics and Security, 19: 6055-6069, 2024 (CCF A類期刊)
2.Y. Chen,H. Wang, W. Li, “Constructing immune-cover for improving holistic security of spatial adaptive steganography,” IEEE Transactions on Information Forensics and Security, DOI 10.1109/TDSC.2024.3376815, 2024 (CCF A類期刊)
3.M. He,H. Wang, F. Zhang, S. Abdullahi, L. Yang, “Robust blind video watermarking against geometric deformations and online video sharing platform processing,” IEEE Transactions on Dependable and Secure Computing, 20(6): 4702-4718, 2023 (CCF A類期刊)
4.Y. Chen, Z. Salcic,H. Wang, K.-K. R. Choo, X. Zhang, “NACA: A joint distortion-based non-additive cost assignment method for video steganography,” IEEE Transactions on Dependable and Secure Computing, 20(3): 2360-2374, 2023 (CCF A類期刊)
5.R. Zhang,H. Wang, M. Du, H. Liu, Y. Zhou, Q. Zeng, “UMMAFormer: A universal multimodal-adaptive transformer framework for temporal forgery localization,” Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), Ottawa, Canada,pp. 8749-8759,2023 (CCF A類國際會議)
6.S. Abdullahi, K. Lv, S. Sun,H. Wang, “Cancelable fingerprint template construction using vector permutation and shift-ordering,” IEEE Transactions on Dependable and Secure Computing, 20(5): 3828-3844, 2023 (CCF A類期刊)
7.Y. Chen,H. Wang, K.-K. R. Choo, P. He, Z. Salcic, D. Kaafar, X. Zhang, “DDCA: A distortion drift-based cost assignment method for adaptive video steganography in the transform domain,” IEEE Transactions on Dependable and Secure Computing, 19(4): 2405-2420, 2022 (CCF A類期刊)
8.Y. Chen,H. Wang, H. Wu, Z. Wu, T. Li, A. Malik, “Adaptive video data hiding through cost assignment and STCs,” IEEE Transactions Dependable and Secure Computing, 18(3): 1320-1335, 2021 (CCF A類期刊)
9.S. Abdullahi,H. Wang, T. Li, “Fractal coding-based robust and alignment-free fingerprint image hashing,” IEEE Transactions on Information Forensics and Security, 15: 2587-2601, 2020 (CCF A類期刊)
10.K. Wang, H. Zhao,H. Wang, “Video steganalysis against motion vector based steganography by adding or subtracting one motion vector value,” IEEE Transactions on Information Forensics and Security, 9(5): 741-751, 2014(CCF A類期刊)
11.M. He,H. Wang, F. Zhang, Y. Xiang, “Exploring accurate invariants on polar harmonic Fourier moments in polar coordinates for robust image watermarking,” IEEE Transactions on Multimedia, 26: 5435-5449, 2024 (CCF B類期刊,中科院一區(qū))
12.W. Li,H. Wang, Y. Chen, “From cover to immucover: adversarial steganography via immunized cover construction,” IEEE Transactions on Fuzzy Systems, 32(3): 1233-1247, 2024 (CCF B類期刊,中科院一區(qū))
13.F. Zhang,H. Wang, M. He, J. Xia, “Robust blind symmetry-based watermarking in the frequency domain against social network processing and desynchronization attacks,” IEEE Transactions on Circuits and Systems for Video Technology, DOI 10.1109/TCSVT.2024.3395802, 2024 (CCF B類期刊,中科院一區(qū))
14.W. Li,H. Wang, Y. Chen, S. Abdullahi, J. Luo, “Constructing immunized stego-image for secure steganography via artificial immune system,” IEEE Transactions on Multimedia, 25: 8320-8333, 2023 (CCF B類期刊,中科院一區(qū))
15.P. He, H. Li,H. Wang, S. Wang, X. Jiang, R. Zhang, “Frame-wise detection of double HEVC compression by learning deep spatio-temporal representations in compression domain,” IEEE Transactions on Multimedia, 23(9): 3192-3192, 2021 (CCF B類期刊,中科院一區(qū))
16.R. Zhang,H. Wang, Ju H. Park, et al., “Secure distributed control for consensus of multiple EL systems subject to DoS attacks,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 54 (6): 3879-3890, 2024 (CCF B類期刊,中科院一區(qū))
17.R. Zhang,H. Wang, Ju H. Park, et al., “Fuzzy secure control for nonlinear N-D parabolic PDE-ODE coupled systems under stochastic deception attacks,” IEEE Transactions on Fuzzy Systems, 30 (8): 3347-3359, 2022 (CCF B類期刊,中科院一區(qū))
18.R. Zhang,H. Wang, Ju H. Park, et al., “Event-triggered impulsive fault-tolerant control for memristor-based RDNNs with actuator faults,” IEEE Transactions on Neural Networks and Learning Systems, 34(6): 2993-3004, 2023 (CCF B類期刊,中科院一區(qū))
19.R. Zhang,H. Wang, Ju H. Park, et al., “Mode-dependent adaptive event-triggered control for stabilization of Markovian memristor-based reaction-diffusion neural networks,” IEEE Transactions on Neural Networks and Learning Systems, 34(8): 3939-3951, 2023 (CCF B類期刊,中科院一區(qū))
20.R. Zhang,H. Wang, Ju H. Park, et al., “Quasisynchronization of reaction-diffusion neural networks under deception attacks,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52 (12): 7833-7844, 2022 (CCF B類期刊,中科院一區(qū))
21.H. Wu, Y.-Q Shi,H. Wang, et al., “Separable reversible data hiding for encrypted palette images with color partitioning and flipping verification,” IEEE Transactions on Circuits and Systems for Video Technology, 27(8): 1620-1631, 2017(CCF B類期刊,中科院一區(qū))
22.P. He, H. Li, B. Li,H. Wang, L. Liu, “Exposing fake bitrate videos using hybrid deep-learning network from recompression error,” IEEE Transactions on Circuits and Systems for Video Technology, 30 (11): 4034-4049, 2020 (CCF B類期刊,中科院一區(qū))
23.Y. Zhou,H. Wang, Q. Zeng, R. Zhang, S. Meng, “A contribution-aware noise feature representation model for image manipulation localization,” Knowledge-Based Systems, 298: 1-11, 2024 (中科院一區(qū))
24.Y. Zhou,H. Wang, Q. Zeng, R. Zhang, S. Meng, “Exploring weakly-supervised image manipulation localization with tampering Edge-based class activation map,” Expert Systems With Applications, 249: 1-12, 2024 (中科院一區(qū))
25.Q. Zeng,H. Wang, Y. Zhou, R. Zhang, S. Meng, “Semi-supervised image manipulation localization with residual enhancement,” Expert Systems With Applications, 252: 1-13, 2024 (中科院一區(qū))
26.M. Zhang,H. Wang, et al., “Exposing unseen GAN-generated image using unsupervised domain adaptation,” Knowledge-Based Systems, 257: 1-14, 2022 (中科院一區(qū))
27.S. Abdullahi, S. Sun, B. Wang, N. Wei,H. Wang, “Biometric template attacks and recent protection mechanisms: A survey,” Information fusion, 103: 102144, 2024 (中科院一區(qū))
28.Y. Xiang,H. Wang, L. Yang, M. He, F. Zhang, “SEDD: robust blind image watermarking with single encoder and dual decoders,” The Computer Journal, doi.org/10.1093/comjnl/bxae014, 2024 (CCF B類期刊)
29.H. Wang,H. Wang, F. Zhang, J. Xia, “Robust watermarking against camera shooting for Powerpoint presentation,” IEEE Signal Processing Letters, 31: 1264-1268, 2024 (JCR二區(qū))
30.Y. Chen,H. Wang, W. Li, J. Luo, “Cost reassignment for improving security of adaptive steganography using an artificial immune system,” IEEE Signal Processing Letters, 29: 1564-1568, 2022 (JCR二區(qū))
31.X. Wu,H. Wang, “Asymmetric contrastive learning for audio fingerprinting,” IEEE Signal Processing Letters, 29: 1873-1877, 2022 (JCR二區(qū))
32.M. Hu,H. Wang, “Image steganalysis against adversarial steganography by combining confidence and pixel artifacts,” IEEE Signal Processing Letters, 30: 987-991, 2023(JCR二區(qū))
33.Y. Li,H. Wang, M. Barni, “A survey of deep neural network watermarking techniques,” Neurocomputing, 461: 171-193, 2021 (JCR二區(qū))
34.J. Li,H. Wang, P. He, S. Abdullahi, B. Li, “Long-term variable Q transform: A novel time-frequency transform algorithm for synthetic speech detection,” Digital Signal Processing, 120: 1-11, 2022 (JCR二區(qū))
35.J. Zhang,H. Wang, P. He, “Dual-branch multi-scale densely connected network for image splicing detection and localization,” Signal Processing: Image Communication, 119: 1-13, 2023 (JCR二區(qū))
36.S. Abdullahi, S. Sun,H. Wang, et al., “The reversibility of cancelable biometric templates based on iterative perturbation stochastic approximation strategy,” Pattern Recognition Letters, 172: 221-229, 2023(JCR二區(qū))
37.A. Malik,H. Wang, et al.,“Reversible data hiding in homomorphically encrypted image using interpolation technique,” Journal of Information Security and Applications, 48: 102374, 2019(JCR二區(qū))
38.F. Zhang,H. Wang, M. He, L. Yang, J. Li, “Adaptive video watermarking with perceptual guarantee and efficiency optimization,”IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP),Seoul, South Korea, 2024(CCF B類國際會議)
39.F. Zhang,H. Wang, M. He, L. Yang, J. Li, “Exploring consistent spatio-temporal distortion and stable 3-D DCT coefficients for robust blind video watermarking,”IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP),Seoul, South Korea, 2024(CCF B類國際會議)
40.H. Wang,H. Wang, X. Huang, Z. Shi, “Enhanced screen shooting resilient document watermarking,” IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP),Seoul, South Korea, 2024(CCF B類國際會議)
41.M. Zhang,H. Wang, P. He, A. Malik, H. Liu, “Improving GAN-generated image detection generalization using unsupervised domain adaptation,” IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, 2022 (CCF B類國際會議)
42.J. Xia,H. Wang, S. Abdullahi, H. Wang, F. Zhang, B. Luo, “Adaptive and robust Fourier-Mellin-based image watermarking for social networking platforms,”IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, pp. 2843-2848, 2023(CCF B類國際會議)
43.Q. Zeng,H. Wang, Y. Zhou, R. Zhang, S. Meng, “A parallel attention mechanism for image manipulation detection and localization,” IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP),Rhodes Island, Greece,2023(CCF B類國際會議)
44.Y. Zhou,H. Wang, Q. Zeng, R. Zhang, S. Meng, “A discriminative multi-channel noise feature representation model for image manipulation localization,” IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP),Rhodes Island, Greece,2023(CCF B類國際會議)
45.P. He, H. Li,H. Wang, “Detection of fake images via the ensemble of deep representations from multi color spaces,” IEEE International Conference on Image Processing (ICIP), 2019, pp. 2299-2303(CCF推薦國際會議)
46.Y. Liu,H. Wang, “Feature selection based on clonal selection algorithm for image steganalysis,” Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 2441-2447, 2023
47.F. Zhang,H. Wang,L. Yang, M. He, “Robust blind video watermarking by constructing spread-spectrum matrix,” IEEE International Workshop on Information Forensics and Security (WIFS), Shanghai, China, 2022
48.Y. Li, L. Abady,H. Wang, M. Barni, “A feature-map-based large-payload DNN watermarking algorithm,” International Workshop on Digital-forensics and Watermarking (IWDW), LNCS 13180, Springer, pp. 135-148, 2022
49.L. Yang,H. Wang, Y. Zhang,et al.,“A robust DCT-based video watermarking scheme against recompression and synchronization attacks,” International Workshop on Digital-forensics and Watermarking (IWDW), LNCS 13180, Springer, pp. 149-162, 2022
50.H. Liu,H. Wang, M. Zhang, “Exposing Deepfake videos using facial decomposition-based domain generalization,” IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), 2022
51.F. Zhang,H. Wang, M. He, J. Li, “Adaptive despread spectrum-based image watermarking for fast product tracking,” International Workshop on Digital-forensics and Watermarking (IWDW), LNCS 13825, Springer, pp. 174-189, 2023
52.H. Wang, J. Sang, “Speaker identity tracing using fingerprint data hiding against telecommunications fraud,” Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 554-559, 2018
53.H. Wang, Z. Chen, et al., “Constructing immune cover for secure steganography based on an artificial immune system approach,” International Workshop on Digital-forensics and Watermarking (IWDW), LNCS 12617, Springer, pp. 53-67, 2021
54.H. Wang, W. Zhang, et al., “Remote authentication of speaker identity based on perceptual fingerprint hashing,” International Workshop on Secure Biometric Technologies (IWSBT), Seoul, Korea, pp. 54-62, 2016 (獲最佳論文獎)
55.S. Abdullahi,H. Wang, A.Malik, “Fingerprint image hashing based on minutiae points and shape context,”International Journal of Digital Crime and Forensics, 10(4): 1-20, 2018 (獲IWDCF 2017最佳論文獎)
56.Y. Chen,H. Wang, et al., “De?ning cost function for robust embedding,”International Conference on Artificial Intelligence and Security(ICAIS), CCIS 1252, Springer, pp. 626-638, 2020 (獲最佳論文獎)
57.袁超,王宏霞,何沛松,“基于注意力機制的高容量通用圖像隱寫模型, ”軟件學(xué)報,35(3): 1502-1514, 2024
58.張玉林,王宏霞,“語義一致性引導(dǎo)的多任務(wù)拼接篡改檢測算法, ”中國圖象圖形學(xué)報,28(3): 775-788, 2023
59.張衛(wèi)明,王宏霞,李斌,任延珍,楊忠良,陳可江,李偉祥,張新鵬,俞能海,“多媒體隱寫研究進展, ”中國圖象圖形學(xué)報,27(6): 1918-1943, 2022
60.章蕾,王宏霞,“用于失配隱寫分析的對抗子領(lǐng)域自適應(yīng)網(wǎng)絡(luò), ”網(wǎng)絡(luò)與信息安全學(xué)報, 8(3): 76-86, 2022
61.張婧媛,王宏霞,何沛松,“基于Transformer的多任務(wù)圖像拼接篡改檢測算法, ”計算機科學(xué), 50(1): 114-122, 2023
62. 韓松源,王宏霞,蔣子渝,“面向流動追蹤的多層魯棒Excel文檔水印, ”計算機科學(xué), 51(5): 374-381, 2024
教育和科研理念
教育理念:每個學(xué)生都有閃光點,不拘一格育人才!
教育文化:師生彼此成就,共同成長!
科研文化:仰望浩瀚星空,探索科學(xué)奧秘,豐收碩果累累!
師生關(guān)系最高境界:亦師亦友,互相欣賞!
教育愿景:以最不競爭的方式,培養(yǎng)出最具競爭力的學(xué)生!
教師寄語
我創(chuàng)造,我快樂!
Let me try!