{"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/vision-llms-can-fool-themselves-with-self","title":"Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks","arxiv_id":"2402.00626","date":"2024-02-01","proceeding":null,"authors":["Maan Qraitem","Nazia Tasnim","Piotr Teterwak","Kate Saenko","Bryan A. Plummer"],"abstract":"Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in personal assistant applications. Previous attacks use simple strategies, such as random misleading words, which don't fully exploit LVLMs' language reasoning abilities. We introduce an experimental setup for testing typographic attacks on LVLMs and propose two novel self-generated attacks: (1) Class-based attacks, where the model identifies a similar class to deceive itself, and (2) Reasoned attacks, where an advanced LVLM suggests an attack combining a deceiving class and description. Our experiments show these attacks significantly reduce classification performance by up to 60\\% and are effective across different models, including InstructBLIP and MiniGPT4. Code: https://github.com/mqraitem/Self-Gen-Typo-Attack","url_abs":"https://arxiv.org/abs/2402.00626v3","url_pdf":"https://arxiv.org/pdf/2402.00626v3.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":"vision-llms-can-fool-themselves-with-self","repo_url":"https://github.com/mqraitem/self-gen-typo-attack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.00626","atlas_url":"https://app.syntology.ai/?focus=2402.00626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00626"}},"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/mqraitem/self-gen-typo-attack","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":8,"samples":[{"code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils_models/utils_gpt4.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils_models/utils_gpt4.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256_prefix":"95bcb0c3cf069e22","entry":"get_gpt4_data","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95bcb0c3cf069e22"}},{"code_sha256_prefix":"b9d472b7f2267e67","entry":"get_gpt4_data_llm","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9d472b7f2267e67"}},{"code_sha256_prefix":"1c1ad9aaa08f3a38","entry":"get_random_data","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c1ad9aaa08f3a38"}},{"code_sha256_prefix":"fb9b530e93968dac","entry":"get_gpt4_llm_pred","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils_models/utils_gpt4.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils_models/utils_gpt4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb9b530e93968dac"}},{"code_sha256_prefix":"e7615cd209323da1","entry":"get_gpt4_pred","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils_models/utils_gpt4.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils_models/utils_gpt4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7615cd209323da1"}},{"code_sha256_prefix":"2e08e894022db180","entry":"run_blip","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils_models/utils_instructblip.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils_models/utils_instructblip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e08e894022db180"}},{"code_sha256_prefix":"b607dd5d1f16b79b","entry":"run_llava","repo":"mqraitem/self-gen-typo-attack","repo_kind":"official","path":"utils_models/utils_llava.py","file_url":"https://github.com/mqraitem/self-gen-typo-attack/blob/HEAD/utils_models/utils_llava.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b607dd5d1f16b79b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}