{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-learning-multi-modal-forgery","title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection","arxiv_id":"2410.23623","date":"2024-10-31","proceeding":null,"authors":["Xiufeng Song","Xiao Guo","Jiache Zhang","Qirui Li","Lei Bai","Xiaoming Liu","Guangtao Zhai","Xiaohong Liu"],"abstract":"Large numbers of synthesized videos from diffusion models pose threats to information security and authenticity, leading to an increasing demand for generated content detection. However, existing video-level detection algorithms primarily focus on detecting facial forgeries and often fail to identify diffusion-generated content with a diverse range of semantics. To advance the field of video forensics, we propose an innovative algorithm named Multi-Modal Detection(MM-Det) for detecting diffusion-generated videos. MM-Det utilizes the profound perceptual and comprehensive abilities of Large Multi-modal Models (LMMs) by generating a Multi-Modal Forgery Representation (MMFR) from LMM's multi-modal space, enhancing its ability to detect unseen forgery content. Besides, MM-Det leverages an In-and-Across Frame Attention (IAFA) mechanism for feature augmentation in the spatio-temporal domain. A dynamic fusion strategy helps refine forgery representations for the fusion. Moreover, we construct a comprehensive diffusion video dataset, called Diffusion Video Forensics (DVF), across a wide range of forgery videos. MM-Det achieves state-of-the-art performance in DVF, demonstrating the effectiveness of our algorithm. Both source code and DVF are available at https://github.com/SparkleXFantasy/MM-Det.","url_abs":"https://arxiv.org/abs/2410.23623v2","url_pdf":"https://arxiv.org/pdf/2410.23623v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-learning-multi-modal-forgery","repo_url":"https://github.com/sparklexfantasy/mm-det","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-forensics","task_name":"Video Forensics"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.23623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23623"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sparklexfantasy/mm-det","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_violates":1,"unverified":22},"by_repo_kind":{"official":{"samples":24,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2d279d661251af46","entry":"sample_continuous","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/process.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/process.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d279d661251af46"}},{"code_sha256_prefix":"d9f67916280ae1e3","entry":"sample_discrete","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/process.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/process.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9f67916280ae1e3"}},{"code_sha256_prefix":"542765e1fd8ceb42","entry":"build_model_with_cfg","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_builder.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"542765e1fd8ceb42"}},{"code_sha256_prefix":"a5b506100733c765","entry":"collate_video_folder_dataset","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/vdataset.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/vdataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5b506100733c765"}},{"code_sha256_prefix":"96047ea1180d5ab6","entry":"collate_video_folder_for_recons_dataset_with_fn","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/vdataset.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/vdataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96047ea1180d5ab6"}},{"code_sha256_prefix":"f4ea0a8791d7d9d4","entry":"create_aa","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/resnet.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4ea0a8791d7d9d4"}},{"code_sha256_prefix":"e12eaf563f19986b","entry":"denormalize_batch_t","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"prepare_reconstructed_dataset.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/prepare_reconstructed_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e12eaf563f19986b"}},{"code_sha256_prefix":"7b8a9c41ab918430","entry":"downsample_conv","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/resnet.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b8a9c41ab918430"}},{"code_sha256_prefix":"defd8a40081ed476","entry":"filter_pretrained_cfg","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_pretrained.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_pretrained.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"defd8a40081ed476"}},{"code_sha256_prefix":"e2b206e653829624","entry":"gaussian_blur","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/process.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/process.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2b206e653829624"}},{"code_sha256_prefix":"71420893c20b5733","entry":"get_arch_name","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_registry.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_registry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71420893c20b5733"}},{"code_sha256_prefix":"8c1ea8436a697a27","entry":"get_dataset_meta","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"prepare_mm_representations.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/prepare_mm_representations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c1ea8436a697a27"}},{"code_sha256_prefix":"295f60cdd29ae30f","entry":"get_default_transformation","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/utils.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"295f60cdd29ae30f"}},{"code_sha256_prefix":"495932ca869a515d","entry":"get_default_transformation_cfg","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/utils.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"495932ca869a515d"}},{"code_sha256_prefix":"10e6af69cd89654c","entry":"get_padding","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/resnet.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10e6af69cd89654c"}},{"code_sha256_prefix":"787ccd49175173ad","entry":"group_with_matcher","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_manipulate.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_manipulate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"787ccd49175173ad"}},{"code_sha256_prefix":"3a0b8256d1b7f59b","entry":"model_parameters","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_manipulate.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_manipulate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3a0b8256d1b7f59b"}},{"code_sha256_prefix":"cd025b18122f9a79","entry":"named_apply","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_manipulate.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_manipulate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd025b18122f9a79"}},{"code_sha256_prefix":"5756c0240fd19e25","entry":"parse_args","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"prepare_mm_representations.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/prepare_mm_representations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5756c0240fd19e25"}},{"code_sha256_prefix":"08cf29ad66c15a74","entry":"pretrained_cfg_for_features","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_builder.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08cf29ad66c15a74"}},{"code_sha256_prefix":"4ed1b18f04138d0d","entry":"random_split_dataset","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"dataset/vdataset.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/dataset/vdataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ed1b18f04138d0d"}},{"code_sha256_prefix":"29a3e687db3fce97","entry":"resolve_pretrained_cfg","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_builder.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29a3e687db3fce97"}},{"code_sha256_prefix":"03e52c96c55bb4b1","entry":"sample_by_interval","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"prepare_mm_representations.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/prepare_mm_representations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03e52c96c55bb4b1"}},{"code_sha256_prefix":"de9c9579e64472b9","entry":"split_model_name_tag","repo":"sparklexfantasy/mm-det","repo_kind":"official","path":"models/vit/_registry.py","file_url":"https://github.com/sparklexfantasy/mm-det/blob/HEAD/models/vit/_registry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de9c9579e64472b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}