{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:53:08Z","timestamp":1781193188280,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-2110198"],"award-info":[{"award-number":["W911NF-2110198"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Homeland Security","award":["17STCIN00001-05-00"],"award-info":[{"award-number":["17STCIN00001-05-00"]}]},{"name":"Cisco Faculty Research Award"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737089","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"415-426","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep IP Protection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9715-0280","authenticated-orcid":false,"given":"Enyan","family":"Dai","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1591-7172","authenticated-orcid":false,"given":"Minhua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3448-4878","authenticated-orcid":false,"given":"Suhang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1615","article-title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","volume":"18","author":"Adi Yossi","year":"2018","unstructured":"Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, and Joseph Keshet. 2018. Turning your weakness into a strength: Watermarking deep neural networks by backdooring. In USENIX Security 18. 1615-1631.","journal-title":"USENIX Security"},{"key":"e_1_3_2_1_2_1","first-page":"1450","article-title":"Certified Neural Network Watermarks with Randomized Smoothing","author":"Bansal Arpit","year":"2022","unstructured":"Arpit Bansal, Ping-Yeh Chiang, Michael J Curry, Rajiv Jain, Curtis Wigington, Varun Manjunatha, John P Dickerson, and Tom Goldstein. 2022. Certified Neural Network Watermarks with Randomized Smoothing. In ICML. 1450-1465.","journal-title":"ICML."},{"key":"e_1_3_2_1_3_1","volume-title":"Xinwei Fan, Osman Cihan Kilinc, and Farinaz Koushanfar.","author":"Chen Huili","year":"2018","unstructured":"Huili Chen, Bita Darvish Rouhani, Xinwei Fan, Osman Cihan Kilinc, and Farinaz Koushanfar. 2018. Performance comparison of contemporary DNN watermarking techniques. arXiv preprint arXiv:1811.03713(2018)."},{"key":"e_1_3_2_1_4_1","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","author":"Cohen Jeremy","year":"2019","unstructured":"Jeremy Cohen, Elan Rosenfeld, and Zico Kolter. 2019. Certified adversarial robustness via randomized smoothing. In ICML. PMLR, 1310-1320.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_5_1","first-page":"579","article-title":"SSLGuard: A watermarking scheme for self-supervised learning pre-trained encoders","author":"Cong Tianshuo","year":"2022","unstructured":"Tianshuo Cong, Xinlei He, and Yang Zhang. 2022. SSLGuard: A watermarking scheme for self-supervised learning pre-trained encoders. In CCS. 579-593.","journal-title":"CCS."},{"key":"e_1_3_2_1_6_1","first-page":"227","article-title":"Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs","author":"Dai Enyan","year":"2021","unstructured":"Enyan Dai, Charu Aggarwal, and Suhang Wang. 2021a. Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. In SIGKDD. 227-236.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_7_1","unstructured":"Enyan Dai and Jie Chen. 2022. Graph-augmented normalizing flows for anomaly detection of multiple time series. arXiv preprint arXiv:2202.07857(2022)."},{"key":"e_1_3_2_1_8_1","first-page":"368","article-title":"A unified framework of graph information bottleneck for robustness and membership privacy","author":"Dai Enyan","year":"2023","unstructured":"Enyan Dai, Limeng Cui, Zhengyang Wang, Xianfeng Tang, Yinghan Wang, Monica Cheng, Bing Yin, and Suhang Wang. 2023a. A unified framework of graph information bottleneck for robustness and membership privacy. In SIGKDD. 368-379.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_9_1","first-page":"181","article-title":"Towards robust graph neural networks for noisy graphs with sparse labels","author":"Dai Enyan","year":"2022","unstructured":"Enyan Dai, Wei Jin, Hui Liu, and Suhang Wang. 2022. Towards robust graph neural networks for noisy graphs with sparse labels. In WSDM. 181-191.","journal-title":"WSDM."},{"key":"e_1_3_2_1_10_1","first-page":"2263","article-title":"Unnoticeable backdoor attacks on graph neural networks","author":"Dai Enyan","year":"2023","unstructured":"Enyan Dai, Minhua Lin, Xiang Zhang, and Suhang Wang. 2023b. Unnoticeable backdoor attacks on graph neural networks. In WWW. 2263-2273.","journal-title":"WWW."},{"key":"e_1_3_2_1_11_1","first-page":"218","article-title":"Labeled data generation with inexact supervision","author":"Dai Enyan","year":"2021","unstructured":"Enyan Dai, Kai Shu, Yiwei Sun, and Suhang Wang. 2021b. Labeled data generation with inexact supervision. In SIGKDD. 218-226.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441752"},{"key":"e_1_3_2_1_13_1","first-page":"302","article-title":"Towards self-explainable graph neural network","author":"Dai Enyan","year":"2021","unstructured":"Enyan Dai and Suhang Wang. 2021b. Towards self-explainable graph neural network. In CIKM. 302-311.","journal-title":"CIKM."},{"key":"e_1_3_2_1_14_1","first-page":"7103","article-title":"Learning fair graph neural networks with limited and private sensitive attribute information","volume":"35","author":"Dai Enyan","year":"2022","unstructured":"Enyan Dai and Suhang Wang. 2022. Learning fair graph neural networks with limited and private sensitive attribute information. TKDE, Vol. 35, 7 (2022), 7103-7117.","journal-title":"TKDE"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689647"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1510-8"},{"key":"e_1_3_2_1_17_1","volume-title":"On random graphs I. Publ. math. debrecen","author":"P","year":"1959","unstructured":"P ERDdS and A R&wi. 1959. On random graphs I. Publ. math. debrecen, Vol. 6, 290-297 (1959), 18."},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Adversarial Robustness in Graph Neural Networks","author":"Hou Zhichao","year":"2024","unstructured":"Zhichao Hou, Minhua Lin, MohamadAli Torkamani, Suhang Wang, and Xiaorui Liu. 2024. Adversarial Robustness in Graph Neural Networks: Recent Advances and New Frontier. In DSAA. IEEE, 1-2.","journal-title":"Recent Advances and New Frontier. In DSAA. IEEE"},{"key":"e_1_3_2_1_19_1","first-page":"594","article-title":"Graphmae: Self-supervised masked graph autoencoders","author":"Hou Zhenyu","year":"2022","unstructured":"Zhenyu Hou, Xiao Liu, Yukuo Cen, Yuxiao Dong, Hongxia Yang, Chunjie Wang, and Jie Tang. 2022. Graphmae: Self-supervised masked graph autoencoders. In SIGKDD. 594-604.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_20_1","volume-title":"Strategies for Pre-training Graph Neural Networks. In International Conference on Learning Representations.","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, and Jure Leskovec. 2020. Strategies for Pre-training Graph Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","unstructured":"Chenao Li Shuo Yan and Enyan Dai. 2025. UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge. arXiv preprint arXiv:2502.06914(2025)."},{"key":"e_1_3_2_1_22_1","unstructured":"Minhua Lin Zhengzhang Chen Yanchi Liu Xujiang Zhao Zongyu Wu Junxiang Wang Xiang Zhang Suhang Wang and Haifeng Chen. 2024. Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation. arXiv preprint arXiv:2410.17462(2024)."},{"key":"e_1_3_2_1_23_1","first-page":"777","article-title":"Stealing Training Graphs from Graph Neural Networks","author":"Lin Minhua","year":"2025","unstructured":"Minhua Lin, Enyan Dai, Junjie Xu, Jinyuan Jia, Xiang Zhang, and Suhang Wang. 2025a. Stealing Training Graphs from Graph Neural Networks. In SIGKDD. 777-788.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_24_1","unstructured":"Minhua Lin Hui Liu Xianfeng Tang Jingying Zeng Zhenwei Dai Chen Luo Zheng Li Xiang Zhang Qi He and Suhang Wang. 2025b. How Far are LLMs from Real Search? A Comprehensive Study on Efficiency Completeness and Inherent Capabilities. arXiv preprint arXiv:2502.18387(2025)."},{"key":"e_1_3_2_1_25_1","first-page":"17008","article-title":"Certifiably robust graph contrastive learning","volume":"36","author":"Lin Minhua","year":"2023","unstructured":"Minhua Lin, Teng Xiao, Enyan Dai, Xiang Zhang, and Suhang Wang. 2023. Certifiably robust graph contrastive learning. NeurIPS, Vol. 36 (2023), 17008-17037.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_26_1","volume-title":"Ssl-wm: A black-box watermarking approach for encoders pre-trained by self-supervised learning. arXiv preprint arXiv:2209.03563(2022).","author":"Lv Peizhuo","year":"2022","unstructured":"Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fan Xiang, Yuling Cai, Hualong Ma, et al., 2022. Ssl-wm: A black-box watermarking approach for encoders pre-trained by self-supervised learning. arXiv preprint arXiv:2209.03563(2022)."},{"key":"e_1_3_2_1_27_1","unstructured":"Alex Nichol Joshua Achiam and John Schulman. 2018. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999(2018)."},{"key":"e_1_3_2_1_28_1","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748(2018)."},{"key":"e_1_3_2_1_29_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155(2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Wenjun Peng Jingwei Yi Fangzhao Wu Shangxi Wu Bin Zhu Lingjuan Lyu Binxing Jiao Tong Xu Guangzhong Sun and Xing Xie. 2023. Are you copying my model? protecting the copyright of large language models for eaas via backdoor watermark. arXiv preprint arXiv:2305.10036(2023).","DOI":"10.18653\/v1\/2023.acl-long.423"},{"key":"e_1_3_2_1_31_1","first-page":"1150","article-title":"Gcc: Graph contrastive coding for graph neural network pre-training","author":"Qiu Jiezhong","year":"2020","unstructured":"Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, and Jie Tang. 2020. Gcc: Graph contrastive coding for graph neural network pre-training. In SIGKDD. 1150-1160.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_32_1","volume-title":"Deepsigns: A generic watermarking framework for ip protection of deep learning models. arXiv preprint arXiv:1804.00750(2018).","author":"Rouhani Bita Darvish","year":"2018","unstructured":"Bita Darvish Rouhani, Huili Chen, and Farinaz Koushanfar. 2018. Deepsigns: A generic watermarking framework for ip protection of deep learning models. arXiv preprint arXiv:1804.00750(2018)."},{"key":"e_1_3_2_1_33_1","unstructured":"Ivanov Sergey Sviridov Sergey and Evgeny Burnaev. 2020. Understanding Isomorphism Bias in Graph Data Sets."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Lujia Shen Shouling Ji Xuhong Zhang Jinfeng Li Jing Chen Jie Shi Chengfang Fang Jianwei Yin and Ting Wang. 2021. Backdoor pre-trained models can transfer to all. arXiv preprint arXiv:2111.00197(2021).","DOI":"10.1145\/3460120.3485370"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"e_1_3_2_1_36_1","first-page":"2120","article-title":"All in one: Multi-task prompting for graph neural networks","author":"Sun Xiangguo","year":"2023","unstructured":"Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan. 2023a. All in one: Multi-task prompting for graph neural networks. In SIGKDD. 2120-2131.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_37_1","unstructured":"Yuchen Sun Tianpeng Liu Panhe Hu Qing Liao Shouling Ji Nenghai Yu Deke Guo and Li Liu. 2023b. Deep Intellectual Property: A Survey. arXiv preprint arXiv:2304.14613(2023)."},{"key":"e_1_3_2_1_38_1","first-page":"269","article-title":"Embedding watermarks into deep neural networks","author":"Uchida Yusuke","year":"2017","unstructured":"Yusuke Uchida, Yuki Nagai, Shigeyuki Sakazawa, and Shin'ichi Satoh. 2017. Embedding watermarks into deep neural networks. In ICMR. 269-277.","journal-title":"ICMR."},{"key":"e_1_3_2_1_39_1","volume-title":"NeurIPS","volume":"31","author":"Virmaux Aladin","year":"2018","unstructured":"Aladin Virmaux and Kevin Scaman. 2018. Lipschitz regularity of deep neural networks: analysis and efficient estimation. NeurIPS, Vol. 31 (2018)."},{"key":"e_1_3_2_1_40_1","first-page":"228","article-title":"Watermarking pre-trained encoders in contrastive learning","author":"Wu Yutong","year":"2022","unstructured":"Yutong Wu, Han Qiu, Tianwei Zhang, Jiwei Li, and Meikang Qiu. 2022. Watermarking pre-trained encoders in contrastive learning. In ICDIS. IEEE, 228-233.","journal-title":"ICDIS. IEEE"},{"key":"e_1_3_2_1_41_1","volume-title":"Lanp: Rethinking the impact of language priors in large vision-language models. arXiv preprint arXiv:2502.12359(2025).","author":"Wu Zongyu","year":"2025","unstructured":"Zongyu Wu, Yuwei Niu, Hongcheng Gao, Minhua Lin, Zhiwei Zhang, Zhifang Zhang, Qi Shi, Yilong Wang, Sike Fu, Junjie Xu, et al., 2025. Lanp: Rethinking the impact of language priors in large vision-language models. arXiv preprint arXiv:2502.12359(2025)."},{"key":"e_1_3_2_1_42_1","volume-title":"MoleculeNet: a benchmark for molecular machine learning. Chemical science","author":"Wu Zhenqin","year":"2018","unstructured":"Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. 2018. MoleculeNet: a benchmark for molecular machine learning. Chemical science, Vol. 9, 2 (2018), 513-530."},{"key":"e_1_3_2_1_43_1","first-page":"1179","article-title":"Watermarking graph neural networks based on backdoor attacks","author":"Xu Jing","year":"2023","unstructured":"Jing Xu, Stefanos Koffas, O\u011fuzhan Ersoy, and Stjepan Picek. 2023. Watermarking graph neural networks based on backdoor attacks. In EuroS&P. IEEE, 1179-1197.","journal-title":"EuroS&P. IEEE"},{"key":"e_1_3_2_1_44_1","unstructured":"Junjie Xu Zongyu Wu Minhua Lin Xiang Zhang and Suhang Wang. 2024. Llm and gnn are complementary: Distilling llm for multimodal graph learning. arXiv preprint arXiv:2406.01032(2024)."},{"key":"e_1_3_2_1_45_1","unstructured":"Yuliang Yan Haochun Tang Shuo Yan and Enyan Dai. 2025. DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection. arXiv preprint arXiv:2505.16530(2025)."},{"key":"e_1_3_2_1_46_1","first-page":"14841","article-title":"Robust watermarking for deep neural networks via bi-level optimization","author":"Yang Peng","year":"2021","unstructured":"Peng Yang, Yingjie Lao, and Ping Li. 2021. Robust watermarking for deep neural networks via bi-level optimization. In ICCV. 14841-14850.","journal-title":"ICCV."},{"key":"e_1_3_2_1_47_1","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. NeurIPS, Vol. 33 (2020), 5812-5823.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_48_1","first-page":"40888","article-title":"Graph contrastive backdoor attacks","author":"Zhang Hangfan","year":"2023","unstructured":"Hangfan Zhang, Jinghui Chen, Lu Lin, Jinyuan Jia, and Dinghao Wu. 2023. Graph contrastive backdoor attacks. In ICML. PMLR, 40888-40910.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196550"},{"key":"e_1_3_2_1_50_1","unstructured":"Zuobai Zhang Minghao Xu Arian Jamasb Vijil Chenthamarakshan Aurelie Lozano Payel Das and Jian Tang. 2022. Protein representation learning by geometric structure pretraining. arXiv preprint arXiv:2203.06125(2022)."},{"key":"e_1_3_2_1_51_1","first-page":"1","article-title":"Watermarking graph neural networks by random graphs","author":"Zhao Xiangyu","year":"2021","unstructured":"Xiangyu Zhao, Hanzhou Wu, and Xinpeng Zhang. 2021. Watermarking graph neural networks by random graphs. In ISDFS. IEEE, 1-6.","journal-title":"ISDFS. IEEE"},{"key":"e_1_3_2_1_52_1","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878(2017)."},{"key":"e_1_3_2_1_53_1","volume-title":"An Empirical Study of Graph Contrastive Learning. arXiv.org(Sept","author":"Zhu Yanqiao","year":"2021","unstructured":"Yanqiao Zhu, Yichen Xu, Qiang Liu, and Shu Wu. 2021. An Empirical Study of Graph Contrastive Learning. arXiv.org(Sept. 2021). arXiv:2109.01116v1 [cs.LG]"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:54:09Z","timestamp":1777571649000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":53,"alternative-id":["10.1145\/3711896.3737089","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737089","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}