{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T04:31:51Z","timestamp":1773808311193,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"42","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking (NNW) as a promising solution. \nAmong various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain generally vulnerable to forging and overwriting attacks.\nTo address those challenges, we propose *NeuralMark*, a robust method built around a *hashed watermark filter*. \nSpecifically, we utilize a hash function to generate an irreversible binary watermark from a secret key, which is then used as a filter to select the model parameters for embedding. \nThis design cleverly intertwines the embedding parameters with the hashed watermark, providing a robust defense against both forging and overwriting attacks.\nAverage pooling is also incorporated to resist fine-tuning and pruning attacks.\nFurthermore, it can be seamlessly integrated into various neural network architectures, ensuring broad applicability.\nWe theoretically analyze its security boundary and highlight the necessity of using a hashed watermark as a filtering mechanism.\nEmpirically, we demonstrate its effectiveness and robustness across 13 distinct Convolutional and Transformer architectures, covering five image classification tasks and one text generation task.<\/jats:p>","DOI":"10.1609\/aaai.v40i42.40915","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:37:01Z","timestamp":1773805021000},"page":"35994-36002","source":"Crossref","is-referenced-by-count":0,"title":["Hashed Watermark as a Filter: A Unified Defense Against Forging and Overwriting Attacks in Neural Network Watermarking"],"prefix":"10.1609","volume":"40","author":[{"given":"Yuan","family":"Yao","sequence":"first","affiliation":[]},{"given":"Jin","family":"Song","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Jin","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40915\/44876","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40915\/44876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:37:02Z","timestamp":1773805022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"42","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i42.40915","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}