{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:21:47Z","timestamp":1783786907562,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"the National Science Foundation for Distinguished Young Scholars","award":["No. 62125604"],"award-info":[{"award-number":["No. 62125604"]}]},{"name":"the Postdoctoral Fellowship Program of CPSF","award":["No. GZC20240826"],"award-info":[{"award-number":["No. GZC20240826"]}]},{"name":"the China Postdoctoral Science Foundation","award":["No. 2024M761679"],"award-info":[{"award-number":["No. 2024M761679"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755711","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"11677-11686","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2333-1064","authenticated-orcid":false,"given":"Shiyao","family":"Cui","sequence":"first","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5270-3801","authenticated-orcid":false,"given":"QingLin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4115-7340","authenticated-orcid":false,"given":"Xuan","family":"Ouyang","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1213-0916","authenticated-orcid":false,"given":"Renmiao","family":"Chen","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9601-3991","authenticated-orcid":false,"given":"Zhexin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4492-9047","authenticated-orcid":false,"given":"Yida","family":"Lu","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6524-9195","authenticated-orcid":false,"given":"Hongning","family":"Wang","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2678-8070","authenticated-orcid":false,"given":"Han","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7111-1849","authenticated-orcid":false,"given":"Minlie","family":"Huang","sequence":"additional","affiliation":[{"name":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Stability AI. [n.d.]. Stable-Diffusion-3.5-Medium. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-3.5-medium"},{"key":"e_1_3_2_2_2_1","unstructured":"Amazon. [n.d.]. Amazon Rekognition Content Moderation. https:\/\/aws.amazon.com\/rekognition\/content-moderation\/"},{"key":"e_1_3_2_2_3_1","unstructured":"Anthropic. 2024. Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"e_1_3_2_2_4_1","unstructured":"Azure. [n.d.]. Azure AI Content Safety Image Moderation. https:\/\/learn.microsoft.com\/en-us\/shows\/responsible-ai\/azure-ai-content-safety-image-moderation"},{"key":"e_1_3_2_2_5_1","unstructured":"Azure. 2023. Azure AI Content Safety. https:\/\/azure.microsoft.com\/en-us\/products\/ai-services\/ai-content-safety"},{"key":"e_1_3_2_2_6_1","unstructured":"Azure. 2024. Analyze multimodal content (preview). https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/content-safety\/quickstart-multimodal"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.13923"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.173"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.05271"},{"key":"e_1_3_2_2_10_1","first-page":"24185","volume-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Zhong Muyan, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), 24185-24198."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106991"},{"key":"e_1_3_2_2_12_1","volume-title":"K. Upasani, and Mahesh Pasupuleti.","author":"Chi Jianfeng","year":"2024","unstructured":"Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan, Eric Smith, Javier Rando, Yiming Zhang, Kate Plawiak, Zacharie Delpierre Coudert, K. Upasani, and Mahesh Pasupuleti. 2024. Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations. ArXiv, Vol. abs\/2411.10414 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274117029"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.18580"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan Anirudh Goyal Anthony Hartshorn Aobo Yang Archi Mitra Archie Sravankumar Artem Korenev Arthur Hinsvark Arun Rao Aston Zhang Aur\u00e9lien Rodriguez Austen Gregerson Ava Spataru Baptiste Rozi\u00e8re Bethany Biron Binh Tang Bobbie Chern Charlotte Caucheteux Chaya Nayak Chloe Bi Chris Marra Chris McConnell Christian Keller Christophe Touret Chunyang Wu Corinne Wong Cristian Canton Ferrer Cyrus Nikolaidis Damien Allonsius Daniel Song Danielle Pintz Danny Livshits David Esiobu Dhruv Choudhary Dhruv Mahajan Diego Garcia-Olano Diego Perino Dieuwke Hupkes Egor Lakomkin Ehab AlBadawy Elina Lobanova Emily Dinan Eric Michael Smith Filip Radenovic Frank Zhang Gabriel Synnaeve Gabrielle Lee Georgia Lewis Anderson Graeme Nail Gr\u00e9goire Mialon Guan Pang Guillem Cucurell Hailey Nguyen Hannah Korevaar Hu Xu Hugo Touvron Iliyan Zarov Imanol Arrieta Ibarra Isabel M. Kloumann Ishan Misra Ivan Evtimov Jade Copet Jaewon Lee Jan Geffert Jana Vranes Jason Park Jay Mahadeokar Jeet Shah Jelmer van der Linde Jennifer Billock Jenny Hong Jenya Lee Jeremy Fu Jianfeng Chi Jianyu Huang Jiawen Liu Jie Wang Jiecao Yu Joanna Bitton Joe Spisak Jongsoo Park Joseph Rocca Joshua Johnstun Joshua Saxe Junteng Jia Kalyan Vasuden Alwala Kartikeya Upasani Kate Plawiak Ke Li Kenneth Heafield Kevin Stone and et al. 2024. The Llama 3 Herd of Models. CoRR Vol. abs\/2407.21783 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2407.21783 arXiv:2407.21783","DOI":"10.48550\/ARXIV.2407.21783"},{"key":"e_1_3_2_2_15_1","unstructured":"Falcons.ai. 2024. Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification. https:\/\/huggingface.co\/Falconsai\/nsfw_image_detection"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.05993"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.09004"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"e_1_3_2_2_19_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Han Seungju","year":"2024","unstructured":"Seungju Han, Kavel Rao, Allyson Ettinger, Liwei Jiang, Bill Yuchen Lin, Nathan Lambert, Yejin Choi, and Nouha Dziri. 2024. WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024,."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.19939"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.06674"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539147"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.01523"},{"key":"e_1_3_2_2_24_1","volume-title":"Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:14113767","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:14113767"},{"key":"e_1_3_2_2_25_1","volume-title":"Visual Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_22"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.18492"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.16971"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.03027"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"e_1_3_2_2_31_1","unstructured":"Meta. 2024. Llama 3.2: Revolutionizing edge AI and vision with open customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.09413"},{"key":"e_1_3_2_2_33_1","first-page":"7","volume-title":"Evaluation of Convolution and Attention Networks for Nudity and Pornography Detection in Sketch Images. 2023 IEEE Symposium on Computers & Informatics (ISCI)","author":"Momo Mhd Adel","year":"2023","unstructured":"Mhd Adel Momo, Hezerul Bin Abdul Karim, Michael Aaron G. Sy, Ahmad Albunni, Myles Joshua Toledo Tan, and Nouar Aldahoul. 2023. Evaluation of Convolution and Attention Networks for Nudity and Pornography Detection in Sketch Images. 2023 IEEE Symposium on Computers & Informatics (ISCI) (2023), 7-12. https:\/\/api.semanticscholar.org\/CorpusID:267044756"},{"key":"e_1_3_2_2_34_1","unstructured":"OpenAI. 2024a. GPT-4o system card. https:\/\/openai.com\/index\/gpt-4o-system-card\/"},{"key":"e_1_3_2_2_35_1","unstructured":"OpenAI. 2024b. GPT-4V(ision) system card. https:\/\/openai.com\/index\/gpt-4v-system-card\/"},{"key":"e_1_3_2_2_36_1","unstructured":"OpenAI. 2024c. Moderate images and text. https:\/\/openai.com\/index\/upgrading-the-moderation-api-with-our-new-multimodal-moderation-model\/"},{"key":"e_1_3_2_2_37_1","unstructured":"Qwen Team. 2025. Qwen2.5-VL-7B-Instruct. https:\/\/huggingface.co\/Qwen\/Qwen2.5-VL-7B-Instruct"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.132"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.12191"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.15279"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.13458"},{"key":"e_1_3_2_2_42_1","volume-title":"ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation. CoRR","author":"Wu Mengyang","year":"1821","unstructured":"Mengyang Wu, Yuzhi Zhao, Jialun Cao, Mingjie Xu, Zhongming Jiang, Xuehui Wang, Qinbin Li, Guangneng Hu, Shengchao Qin, and Chi-Wing Fu. 2024. ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation. CoRR, Vol. abs\/2412.18216 (2024)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.182"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.742"},{"key":"e_1_3_2_2_45_1","volume-title":"BingoGuard: LLM Content Moderation Tools with Risk Levels. In ICLR","author":"Yin Fan","year":"2025","unstructured":"Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Divyansh Agarwal, Caiming Xiong, and Chien-Sheng Wu. 2025. BingoGuard: LLM Content Moderation Tools with Risk Levels. In ICLR 2025."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.21772"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.12030"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.830"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.610"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_8"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.06172"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"e_1_3_2_2_53_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=1tZbq88f27"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:40:15Z","timestamp":1765309215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3755711","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755711","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}