{"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/x-transfer-attacks-towards-super-transferable","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","arxiv_id":"2505.05528","date":"2025-05-08","proceeding":null,"authors":["Hanxun Huang","Sarah Erfani","Yige Li","Xingjun Ma","James Bailey"],"abstract":"As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a critical concern. In this work, we introduce \\textbf{X-Transfer}, a novel attack method that exposes a universal adversarial vulnerability in CLIP. X-Transfer generates a Universal Adversarial Perturbation (UAP) capable of deceiving various CLIP encoders and downstream VLMs across different samples, tasks, and domains. We refer to this property as \\textbf{super transferability}--a single perturbation achieving cross-data, cross-domain, cross-model, and cross-task adversarial transferability simultaneously. This is achieved through \\textbf{surrogate scaling}, a key innovation of our approach. Unlike existing methods that rely on fixed surrogate models, which are computationally intensive to scale, X-Transfer employs an efficient surrogate scaling strategy that dynamically selects a small subset of suitable surrogates from a large search space. Extensive evaluations demonstrate that X-Transfer significantly outperforms previous state-of-the-art UAP methods, establishing a new benchmark for adversarial transferability across CLIP models. The code is publicly available in our \\href{https://github.com/HanxunH/XTransferBench}{GitHub repository}.","url_abs":"https://arxiv.org/abs/2505.05528v1","url_pdf":"https://arxiv.org/pdf/2505.05528v1.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":"x-transfer-attacks-towards-super-transferable","repo_url":"https://github.com/HanxunH/XTransferBench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[{"slug":"x-transferbench","name":"X-TransferBench","full_name":"X-TransferBench"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.05528","atlas_url":"https://app.syntology.ai/?focus=2505.05528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05528"}},"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/HanxunH/XTransferBench","reach":null}],"summary":{"ran_draft_wrong":4,"ran":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"7662cfed0965f296","entry":"custom_collate_fn","repo":"hanxunh/xtransferbench","repo_kind":"official","path":"evaluations/eval_blip2.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/evaluations/eval_blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7662cfed0965f296"}},{"code_sha256_prefix":"de79b9565f0267ad","entry":"XTransferLinf","repo":"HanxunH/XTransferBench","repo_kind":"official","path":"src/XTransferBench/attacker/xtransfer.py","file_url":"https://github.com/HanxunH/XTransferBench/blob/HEAD/src/XTransferBench/attacker/xtransfer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de79b9565f0267ad"}},{"code_sha256_prefix":"2ed5f99d405e8fbe","entry":"pre_caption","repo":"hanxunh/xtransferbench","repo_kind":"official","path":"xtransfer/datasets/caption_dataset.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/xtransfer/datasets/caption_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ed5f99d405e8fbe"}},{"code_sha256_prefix":"097b2f3239620b1a","entry":"pre_captions","repo":"hanxunh/xtransferbench","repo_kind":"official","path":"xtransfer/datasets/caption_dataset.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/xtransfer/datasets/caption_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"097b2f3239620b1a"}},{"code_sha256_prefix":"d85c705653a8ceef","entry":"total_variation_loss","repo":"hanxunh/xtransferbench","repo_kind":"official","path":"xtransfer/attacks/attack_generation.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/xtransfer/attacks/attack_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d85c705653a8ceef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}