{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T12:10:06Z","timestamp":1751544606220,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1145\/3709020.3734834","type":"proceedings-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T11:28:01Z","timestamp":1751542081000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8615-435X","authenticated-orcid":false,"given":"Van-Hoang","family":"Phan","sequence":"first","affiliation":[{"name":"University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6197-3428","authenticated-orcid":false,"given":"Long-Khanh","family":"Pham","sequence":"additional","affiliation":[{"name":"University of Science, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam and FPT Software AI Center, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3268-024X","authenticated-orcid":false,"given":"Dang","family":"Vu","sequence":"additional","affiliation":[{"name":"University of Science, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam and FPT Software AI Center, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8036-954X","authenticated-orcid":false,"given":"Anh-Duy","family":"Tran","sequence":"additional","affiliation":[{"name":"DistriNet, KU Leuven, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3044-8175","authenticated-orcid":false,"given":"Minh-Son","family":"Dao","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,24]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01452"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Nadia Alonso-L\u00f3pez Pavel Sidorenko\u00a0Bautista and F\u00e1bio Giacomelli. 2021. Beyond Challenges and Viral Dance Moves: TikTok as a Vehicle for Disinformation and Fact-Checking in Spain Portugal Brazil and the USA. An\u00e0lisi 64 (06 2021) 65\u201384. 10.5565\/rev\/analisi.3411>","DOI":"10.5565\/rev\/analisi.3411>"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26648"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Sarah Evanega Mark Lynas Jordan Adams and Karinne Smolenyak. 2020. Coronavirus misinformation: quantifying sources and themes in the COVID-19 \u2018infodemic\u2019 (Preprint). 10.2196\/preprints.25143","DOI":"10.2196\/preprints.25143"},{"key":"e_1_3_3_1_6_2","unstructured":"Lisa Fazio. 2020. Out-of-context photos are a powerful low-tech form of misinformation. The Conversation 14 1 (2020)."},{"key":"e_1_3_3_1_7_2","unstructured":"Yimeng Gu Mengqi Zhang Ignacio Castro Shu Wu and Gareth Tyson. 2024. Learning Domain-Invariant Features for Out-of-Context News Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.07430 (2024)."},{"key":"e_1_3_3_1_8_2","unstructured":"Shaohan Huang Li Dong Wenhui Wang Yaru Hao Saksham Singhal Shuming Ma Tengchao Lv Lei Cui Owais\u00a0Khan Mohammed Barun Patra et\u00a0al. 2023. Language is not all you need: Aligning perception with language models. Advances in Neural Information Processing Systems 36 (2023) 72096\u201372109."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123385"},{"key":"e_1_3_3_1_10_2","first-page":"11330","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jaiswal Ayush","year":"2019","unstructured":"Ayush Jaiswal, Yue Wu, Wael AbdAlmageed, Iacopo Masi, and Premkumar Natarajan. 2019. Aird: Adversarial learning framework for image repurposing detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11330\u201311339."},{"key":"e_1_3_3_1_11_2","unstructured":"Liunian\u00a0Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.03557 (2019)."},{"key":"e_1_3_3_1_12_2","unstructured":"Yihui Li Xiaoyue Yan Hao Zhou and Borong Lin. 2024. Question Answering for Decisionmaking in Green Building Design: A Multimodal Data Reasoning Method Driven by Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04741 (2024)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Piper Liu and Vincent Huang. 2020. Digital Disinformation About COVID-19 and the Third-Person Effect: Examining the Channel Differences and Negative Emotional Outcomes. Cyberpsychology Behavior and Social Networking 23 (07 2020). 10.1089\/cyber.2020.0363","DOI":"10.1089\/cyber.2020.0363"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Grace Luo Trevor Darrell and Anna Rohrbach. 2021. Newsclippings: Automatic generation of out-of-context multimodal media. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.05893 (2021).","DOI":"10.18653\/v1\/2021.emnlp-main.545"},{"key":"e_1_3_3_1_15_2","first-page":"2819","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Mu Michael","year":"2023","unstructured":"Michael Mu, Sreyasee Das\u00a0Bhattacharjee, and Junsong Yuan. 2023. Self-supervised distilled learning for multi-modal misinformation identification. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 2819\u20132828."},{"key":"e_1_3_3_1_16_2","unstructured":"Alex Nikolov Giovanni Da\u00a0San Martino Ivan Koychev and Preslav Nakov. 2020. Team Alex at CLEF CheckThat! 2020: Identifying Check-Worthy Tweets With Transformer Models. arxiv:https:\/\/arXiv.org\/abs\/2009.02931\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2009.02931"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592572.3592842"},{"key":"e_1_3_3_1_18_2","unstructured":"Stefanos-Iordanis Papadopoulos Christos Koutlis Symeon Papadopoulos and Panagiotis\u00a0C Petrantonakis. 2023. Red-dot: Multimodal fact-checking via relevant evidence detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.09939 (2023)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Long-Khanh Pham Hoa-Vien Vo-Hoang and Anh-Duy Tran. 2024. A Generative Adaptive Context Learning Framework for Large Language Models in Cheapfake Detection(ICMR \u201924). Association for Computing Machinery New York NY USA 1288\u20131293. https:\/\/doi.org\/10.1145\/3652583.3657597","DOI":"10.1145\/3652583.3657597"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.trustnlp-1.28"},{"key":"e_1_3_3_1_21_2","unstructured":"Shraman Pramanick Rama Chellappa and Subhashini Venugopalan. 2025. SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers. arxiv:https:\/\/arXiv.org\/abs\/2407.09413\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.09413"},{"key":"e_1_3_3_1_22_2","first-page":"13052","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Qi Peng","year":"2024","unstructured":"Peng Qi, Zehong Yan, Wynne Hsu, and Mong\u00a0Li Lee. 2024. Sniffer: Multimodal large language model for explainable out-of-context misinformation detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 13052\u201313062."},{"key":"e_1_3_3_1_23_2","unstructured":"Shuofei Qiao Yixin Ou Ningyu Zhang Xiang Chen Yunzhi Yao Shumin Deng Chuanqi Tan Fei Huang and Huajun Chen. 2023. Reasoning with Language Model Prompting: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2212.09597\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2212.09597"},{"key":"e_1_3_3_1_24_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240707"},{"key":"e_1_3_3_1_26_2","unstructured":"Ian Sample. 2020. What are deepfakes \u2013 and how can you spot them?"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679826"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Aythami Morales and Javier Ortega-Garcia. 2020. Deepfakes and beyond: A survey of face manipulation and fake detection. Information Fusion 64 (2020) 131\u2013148.","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.448"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3657596"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01450"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"e_1_3_3_1_34_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2201.11903\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_3_1_35_2","unstructured":"Tianhe Wu Kede Ma Jie Liang Yujiu Yang and Lei Zhang. 2024. A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment. arxiv:https:\/\/arXiv.org\/abs\/2403.10854\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2403.10854"},{"key":"e_1_3_3_1_36_2","unstructured":"Haotian Xia Zhengbang Yang Junbo Zou Rhys Tracy Yuqing Wang Chi Lu Christopher Lai Yanjun He Xun Shao Zhuoqing Xie Yuan fang Wang Weining Shen and Hanjie Chen. 2024. SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2410.08474\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2410.08474"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Xin Yuan Jie Guo Weidong Qiu Zheng Huang and Shujun Li. 2023. Support or refute: Analyzing the stance of evidence to detect out-of-context mis-and disinformation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.01766 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.259"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612183"},{"key":"e_1_3_3_1_39_2","unstructured":"Yizhou Zhang Loc Trinh Defu Cao Zijun Cui and Yan Liu. 2024. Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model. arxiv:https:\/\/arXiv.org\/abs\/2304.07633\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2304.07633"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1007\/978-3-030-47436-2_27","volume-title":"Pacific-Asia Conference on knowledge discovery and data mining","author":"Zhou Xinyi","year":"2020","unstructured":"Xinyi Zhou, Jindi Wu, and Reza Zafarani. 2020. : Similarity-aware multi-modal fake news detection. In Pacific-Asia Conference on knowledge discovery and data mining. Springer, 354\u2013367."}],"event":{"name":"SCID '25: The 2nd Workshop on Security-Centric Strategies for Combating Information Disorder","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"location":"Hanoi Vietnam","acronym":"SCID '25"},"container-title":["Proceedings of the 2nd Workshop on Security-Centric Strategies for Combating Information Disorder"],"original-title":[],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T11:28:07Z","timestamp":1751542087000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709020.3734834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,24]]},"references-count":40,"alternative-id":["10.1145\/3709020.3734834","10.1145\/3709020"],"URL":"https:\/\/doi.org\/10.1145\/3709020.3734834","relation":{},"subject":[],"published":{"date-parts":[[2025,8,24]]},"assertion":[{"value":"2025-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}