{"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-fused-attack-advancing-aggressive-and","title":"Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation","arxiv_id":"2409.05021","date":"2024-09-08","proceeding":null,"authors":["Yanni Xue","Haojie Hao","Jiakai Wang","Qiang Sheng","Renshuai Tao","Yu Liang","Pu Feng","Xianglong Liu"],"abstract":"While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus drawing increased research attention. However, existing studies on adversarial attacks are insufficient in both attacking ability and human imperceptibility due to their sole focus on the scope of language. This paper proposes a novel vision-fused attack (VFA) framework to acquire powerful adversarial text, i.e., more aggressive and stealthy. Regarding the attacking ability, we design the vision-merged solution space enhancement strategy to enlarge the limited semantic solution space, which enables us to search for adversarial candidates with higher attacking ability. For human imperceptibility, we propose the perception-retained adversarial text selection strategy to align the human text-reading mechanism. Thus, the finally selected adversarial text could be more deceptive. Extensive experiments on various models, including large language models (LLMs) like LLaMA and GPT-3.5, strongly support that VFA outperforms the comparisons by large margins (up to 81%/14% improvements on ASR/SSIM).","url_abs":"https://arxiv.org/abs/2409.05021v1","url_pdf":"https://arxiv.org/pdf/2409.05021v1.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-fused-attack-advancing-aggressive-and","repo_url":"https://github.com/levelower/vfa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-text","task_name":"Adversarial Text"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.05021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05021"}},"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":"deterministic:regex_extraction","url":"https://github.com/Levelower/VFA","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":4,"samples":[{"code_sha256_prefix":"b13d2218dfb23d83","entry":"Attacker","repo":"Levelower/VFA","repo_kind":"official","path":"attack.py","file_url":"https://github.com/Levelower/VFA/blob/HEAD/attack.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":"b13d2218dfb23d83"}},{"code_sha256_prefix":"68cc61769ca9aad1","entry":"importance_model","repo":"Levelower/VFA","repo_kind":"official","path":"attack.py","file_url":"https://github.com/Levelower/VFA/blob/HEAD/attack.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":"68cc61769ca9aad1"}},{"code_sha256_prefix":"34e05c31908555e0","entry":"pixel_model","repo":"Levelower/VFA","repo_kind":"official","path":"attack.py","file_url":"https://github.com/Levelower/VFA/blob/HEAD/attack.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":"34e05c31908555e0"}},{"code_sha256_prefix":"ca3a73c9a03415b2","entry":"semantics_model","repo":"Levelower/VFA","repo_kind":"official","path":"attack.py","file_url":"https://github.com/Levelower/VFA/blob/HEAD/attack.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":"ca3a73c9a03415b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}