HW
Hanzhou Wu
cs.CRcs.MMcs.CLcs.CVcs.LGcs.AIAdversarial attackComputer Securitycs.DScs.IT
On Valency
published · living versionsW_gu4hfrmf·v1 · currentpublished
Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models
with Yanan He, Yanli Chen, Ling Xiong, Gejian Zhao
1 version
W_9ch3bref·v1published
Preprints & journals
45 papers in the corpus · 2016–2025Efficient Privacy-Preserving Face Recognition Based on Feature Encoding and Symmetric Homomorphic Encryption.41593912 · Zhou, Limengnan, Li, Qinshi, Zhu, Hui et al.2026 · 0 citationsEntropy (Basel, Switzerland). 2025;28(1)
Defining Cost Function of Steganography with Large Language Models2512.09769v3 · Hanzhou Wu, Yige Wang2025 · 0 citationsIS&T Electronic Imaging, Media Watermarking, Security, and Forensics (2026)
Rotation, Scale, and Translation Resilient Black-box Fingerprinting for Intellectual Property Protection of EaaS Models2510.16706v1 · Hongjie Zhang, Zhiqi Zhao, Hanzhou Wu et al.2025 · 0 citationsarXiv
An Information Asymmetry Game for Trigger-based DNN Model Watermarking2510.14218v1 · Chaoyue Huang, Gejian Zhao, Hanzhou Wu et al.2025 · 0 citationsIEEE International Symposium on Digital Forensics and Security (2026)
Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron2509.19101v1 · Gejian Zhao, Hanzhou Wu, Xinpeng Zhang2025 · 0 citationsarXiv
Yet Another Watermark for Large Language Models2509.12574v2 · Siyuan Bao, Ying Shi, Zhiguang Yang et al.2025 · 1 citationInternational Conference on Communications and Broadband Networking (2025)
Dormant key: Unlocking universal adversarial control in text-to-image models.40945018 · Hu, Jingqi, Li, Li, Wu, Hanzhou et al.2025 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;193:108065
Watermarking Quantum Neural Networks Based on Sample Grouped and Paired Training2506.12675v1 · Limengnan Zhou, Hanzhou Wu2025 · 0 citationsInternational Conference on Frontiers in Cyber Security (FCS'2025)
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs2504.05605v1 · Gejian Zhao, Hanzhou Wu, Xinpeng Zhang et al.2025 · 1 citationIEEE Transactions on Information Forensics and Security (2026)
A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking2501.01194v1 · Chaoyue Huang, Hanzhou Wu2025 · 2 citationsIEEE International Symposium on Digital Forensics and Security 2025
New Families of Frequency-Hopping Sequence Sets with a Low-Hit-Zone.39593892 · Zhou, Limengnan, Wu, Hanzhou2024 · 1 citationEntropy (Basel, Switzerland). 2024;26(11)
Discriminative Anchor Learning for Efficient Multi-view Clustering2409.16904v1 · Yalan Qin, Nan Pu, Hanzhou Wu et al.2024 · 15 citationsarXiv
TCNFormer: Temporal Convolutional Network Former for Short-Term Wind Speed Forecasting2408.15737v1 · Abid Hasan Zim, Aquib Iqbal, Asad Malik et al.2024 · 5 citationsarXiv
Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings2406.13177v3 · Xiangyu Zhao, Hanzhou Wu, Xinpeng Zhang2024 · 1 citationIEEE International Workshop on Information Forensics and Security (IEEE WIFS'2024)
StegGuard: Fingerprinting Self-supervised Pre-trained Encoders via Secrets Embeder and Extractor2310.03380v1 · Xingdong Ren, Tianxing Zhang, Hanzhou Wu et al.2023 · 0 citationsarXiv
Generative Model Watermarking Suppressing High-Frequency Artifacts2305.12391v1 · Li Zhang, Yong Liu, Xinpeng Zhang et al.2023 · 0 citationsACM Workshop on Information Hiding and Multimedia Security (ACM IH&MMSec'2024)
JPEG Steganalysis Based on Steganographic Feature Enhancement and Graph Attention Learning2302.02276v1 · Qiyun Liu, Zhiguang Yang, Hanzhou Wu2023 · 6 citationsJournal of Electronic Imaging 2023
Generative Model Watermarking Based on Human Visual System2209.15268v1 · Li Zhang, Yong Liu, Shaoteng Liu et al.2022 · 4 citations19th International Forum of Digital Multimedia Communication (2022)
Reversible Data Hiding in Encrypted Text Using Paillier Cryptosystem2209.11802v1 · Asad Malik, Aeyan Ashraf, Hanzhou Wu et al.2022 · 2 citationsAPSIPA Annual Summit and Conference 2022
Robust and Lossless Fingerprinting of Deep Neural Networks via Pooled Membership Inference2209.04113v2 · Hanzhou Wu2022 · 4 citationsIEEE International Conference on High Performance Computing and Communications 2022 (AR: 117/663 = 17.6%)
Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering2208.03944v2 · Yong Liu, Hanzhou Wu, Xinpeng Zhang2022 · 23 citationsIEEE Transactions on Dependable and Secure Computing (Final version at IEEE, 2024)
AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning2208.03948v1 · Tianxing Zhang, Hanzhou Wu, Xiaofeng Lu et al.2022 · 7 citationsApplied Sciences (2023)
General Framework for Reversible Data Hiding in Texts Based on Masked Language Modeling2206.10112v1 · Xiaoyan Zheng, Yurun Fang, Hanzhou Wu2022 · 2 citationsIEEE International Workshop on Multimedia Signal Processing (2022)
Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples2205.04145v2 · Lina Lin, Hanzhou Wu2022 · 5 citationsIEEE International Symposium on Digital Forensics and Security 2022 (Final version at IEEE Xplore)
Autoregressive Linguistic Steganography Based on BERT and Consistency Coding2203.13972v1 · Xiaoyan Zheng, Hanzhou Wu2022 · 14 citationsSecurity and Communication Networks (2022) Open Access
Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding2203.03795v1 · Tianyu Yang, Hanzhou Wu, Biao Yi et al.2022 · 42 citationsIEEE Transactions on Dependable and Secure Computing (Final version at IEEE, 2023)
Semi-Supervised Structured Subspace Learning for Multi-View Clustering.34807827 · Qin, Yalan, Wu, Hanzhou, Zhang, Xinpeng et al.2021 · 73 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2022;31:1-14
Generating Watermarked Adversarial Texts2110.12948v1 · Mingjie Li, Hanzhou Wu, Xinpeng Zhang2021 · 2 citationsJournal of Electronic Imaging (2023)
Graph Representation Learning for Spatial Image Steganalysis2110.00957v3 · Qiyun Liu, Hanzhou Wu2021 · 3 citationsIEEE International Workshop on Multimedia Signal Processing (2022)
Exploiting Language Model for Efficient Linguistic Steganalysis2107.12168v3 · Biao Yi, Hanzhou Wu, Guorui Feng et al.2021 · 11 citationsarXiv
Structural Watermarking to Deep Neural Networks via Network Channel Pruning2107.08688v2 · Xiangyu Zhao, Yinzhe Yao, Hanzhou Wu et al.2021 · 40 citationsarXiv
Generalized Reversible Data Hiding with Content-Adaptive Operation and Fast Histogram Shifting Optimization.34356458 · Zhou, Limengnan, Han, Hongyu, Wu, Hanzhou2021 · 3 citationsEntropy (Basel, Switzerland). 2021;23(7)
Hiding Data Hiding2102.06826v3 · Hanzhou Wu, Gen Liu, Xinpeng Zhang2021 · 0 citationsFinal version goes to Pattern Recognition Letters (2022)
Orientation Convolutional Networks for Image Recognition2102.01523v1 · Yalan Qin, Guorui Feng, Hanzhou Wu et al.2021 · 0 citationsarXiv
Watermarking Graph Neural Networks by Random Graphs2011.00512v2 · Xiangyu Zhao, Hanzhou Wu, Xinpeng Zhang2020 · 43 citationsIEEE International Symposium on Digital Forensics and Security (2021)
Game-theoretic Analysis to Content-adaptive Reversible Watermarking1905.01674v1 · Hanzhou Wu, Xinpeng Zhang2019 · 3 citationsarXiv
Steganographer Identification1904.07554v1 · Hanzhou Wu2019 · 7 citationsarXiv
Feature Bagging for Steganographer Identification1810.11973v1 · Hanzhou Wu2018 · 2 citationsarXiv
The Cut and Dominating Set Problem in A Steganographer Network1802.09333v1 · Hanzhou Wu, Wei Wang, Jing Dong et al.2018 · 0 citationsarXiv
Ensemble Reversible Data Hiding1801.04747v4 · Hanzhou Wu, Wei Wang, Jing Dong et al.2018 · 4 citationsarXiv
Minimizing Embedding Distortion with Weighted Bigraph Matching in Reversible Data Hiding1712.06240v1 · Hanzhou Wu2017 · 4 citationsarXiv
A Graph-theoretic Model to Steganography on Social Networks1712.03621v5 · Hanzhou Wu, Wei Wang, Jing Dong et al.2017 · 3 citationsarXiv
Can Machine Learn Steganography? - Implementing LSB Substitution and Matrix Coding Steganography with Feed-Forward Neural Networks1606.05294v1 · Han-Zhou Wu, Hong-Xia Wang, Yun-Qing Shi2016 · 10 citationsarXiv
Prediction-error of Prediction Error (PPE)-based Reversible Data Hiding1604.04984v5 · Han-Zhou Wu, Hong-Xia Wang, Yun-Qing Shi2016 · 27 citationsarXiv
Optimal Binary Coding for -state Data Embedding1604.03140v1 · Han-Zhou Wu2016 · 0 citationsarXiv
Career total: at least 173 works. 45 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.