{"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/antifakeprompt-prompt-tuned-vision-language","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","arxiv_id":"2310.17419","date":"2023-10-26","proceeding":null,"authors":["You-Ming Chang","Chen Yeh","Wei-Chen Chiu","Ning Yu"],"abstract":"Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach called AntifakePrompt, using VLMs (e.g., InstructBLIP) and prompt tuning techniques to improve the deepfake detection accuracy over unseen data. We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to answer the real/fake information of a query image. We conduct full-spectrum experiments on datasets from a diversity of 3 held-in and 20 held-out generative models, covering modern text-to-image generation, image editing and adversarial image attacks. These testing datasets provide useful benchmarks in the realm of deepfake detection for further research. Moreover, results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 71.06% to 92.11%, in average accuracy over unseen domains) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of training data and trainable parameters, resulting in an effective and efficient solution for deepfake detection. Code and models can be found at https://github.com/nctu-eva-lab/AntifakePrompt.","url_abs":"https://arxiv.org/abs/2310.17419v3","url_pdf":"https://arxiv.org/pdf/2310.17419v3.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":"antifakeprompt-prompt-tuned-vision-language","repo_url":"https://github.com/nctu-eva-lab/antifakeprompt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"misinformation","task_name":"Misinformation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.17419","atlas_url":"https://app.syntology.ai/?focus=2310.17419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17419"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/nctu-eva-lab/antifakeprompt","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"56f02812d66a0d11","entry":"generate_caption","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/caption.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/caption.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"56f02812d66a0d11"}},{"code_sha256_prefix":"92f2e16ee0d3a24d","entry":"get_concat_v","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/dataset_browser.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/dataset_browser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"92f2e16ee0d3a24d"}},{"code_sha256_prefix":"3d63c3c2af355251","entry":"print_combine_result","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"deepfake-detection/blip2_t5_instruct.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/deepfake-detection/blip2_t5_instruct.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3d63c3c2af355251"}},{"code_sha256_prefix":"13a43a7d815937e6","entry":"read_img","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/calculate_coco_features.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/calculate_coco_features.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"13a43a7d815937e6"}},{"code_sha256_prefix":"926bb38f979a61ef","entry":"resize_img","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/utils.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"926bb38f979a61ef"}},{"code_sha256_prefix":"f809f2ecf34c1c99","entry":"resize_img_w","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/dataset_browser.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/dataset_browser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f809f2ecf34c1c99"}},{"code_sha256_prefix":"3d4bbb5ca53fd24a","entry":"sample_dataset","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/dataset_browser.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/dataset_browser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3d4bbb5ca53fd24a"}},{"code_sha256_prefix":"3e12ea8c09674aa8","entry":"compute_gradcam_batch","repo":"nctu-eva-lab/antifakeprompt","repo_kind":"official","path":"app/multimodal_search.py","file_url":"https://github.com/nctu-eva-lab/antifakeprompt/blob/HEAD/app/multimodal_search.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3e12ea8c09674aa8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}