{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/adversarial-text","name":"Adversarial Text","slug":"adversarial-text","description_markdown":"Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.","categories":[{"name":"Adversarial","url":"/area/adversarial"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":114,"papers_with_code":51,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/harmfultasks","name":"HarmfulTasks","full_name":"Harmful and Malicious Tasks for LLMs in Jailbreaking Prompts","num_papers_in_archive":1},{"url":"/dataset/texygen-platform","name":"Texygen Platform","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/adversarial-attack","name":"Adversarial Attack"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":114,"of_with_code":51,"tagged_in_all":114,"counts":{"archive_papers_tagged":114,"with_a_code_link":51,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":114,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/generative-adversarial-text-to-image","slug":"generative-adversarial-text-to-image","title":"Generative Adversarial Text to Image Synthesis","date":"2016-05-17","arxiv_id":"1605.05396","repositories_listed":39,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generative-adversarial-text-to-image#ran","syntology_url":"https://syntology.ai/paper/1605.05396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.05396"}},"official":{"repos":["reedscot/icml2016"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/is-bert-really-robust-natural-language-attack","slug":"is-bert-really-robust-natural-language-attack","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","date":"2019-07-27","arxiv_id":"1907.11932","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-bert-really-robust-natural-language-attack#ran","syntology_url":"https://syntology.ai/paper/1907.11932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11932"}},"official":{"repos":["jind11/TextFooler"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/retsim-resilient-and-efficient-text","slug":"retsim-resilient-and-efficient-text","title":"RETSim: Resilient and Efficient Text Similarity","date":"2023-11-28","arxiv_id":"2311.17264","repositories_listed":3,"syntology":null},{"url":"/paper/generating-natural-language-attacks-in-a-hard","slug":"generating-natural-language-attacks-in-a-hard","title":"Generating Natural Language Attacks in a Hard Label Black Box Setting","date":"2020-12-29","arxiv_id":"2012.14956","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-natural-language-attacks-in-a-hard#ran","syntology_url":"https://syntology.ai/paper/2012.14956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.14956"}},"official":{"repos":["RishabhMaheshwary/hard-label-attack"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/advcodec-towards-a-unified-framework-for-1","slug":"advcodec-towards-a-unified-framework-for-1","title":"T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack","date":"2019-12-22","arxiv_id":"1912.10375","repositories_listed":3,"syntology":null},{"url":"/paper/semantic-preserving-adversarial-text-attacks","slug":"semantic-preserving-adversarial-text-attacks","title":"Semantic-Preserving Adversarial Text Attacks","date":"2021-08-23","arxiv_id":"2108.10015","repositories_listed":2,"syntology":null},{"url":"/paper/searching-for-a-search-method-benchmarking","slug":"searching-for-a-search-method-benchmarking","title":"Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples","date":"2020-09-09","arxiv_id":"2009.06368","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-adversarial-text-to-speech","slug":"end-to-end-adversarial-text-to-speech","title":"End-to-End Adversarial Text-to-Speech","date":"2020-06-05","arxiv_id":"2006.03575","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":7,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-adversarial-text-to-speech#ran","syntology_url":"https://syntology.ai/paper/2006.03575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03575"}},"official":null}},{"url":"/paper/textattack-a-framework-for-adversarial","slug":"textattack-a-framework-for-adversarial","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","date":"2020-04-29","arxiv_id":"2005.05909","repositories_listed":2,"syntology":null},{"url":"/paper/bae-bert-based-adversarial-examples-for-text","slug":"bae-bert-based-adversarial-examples-for-text","title":"BAE: BERT-based Adversarial Examples for Text Classification","date":"2020-04-04","arxiv_id":"2004.01970","repositories_listed":2,"syntology":null},{"url":"/paper/black-box-generation-of-adversarial-text","slug":"black-box-generation-of-adversarial-text","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","date":"2018-01-13","arxiv_id":"1801.04354","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/black-box-generation-of-adversarial-text#ran","syntology_url":"https://syntology.ai/paper/1801.04354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.04354"}},"official":{"repos":["QData/deepWordBug"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stealthrank-llm-ranking-manipulation-via","slug":"stealthrank-llm-ranking-manipulation-via","title":"StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization","date":"2025-04-08","arxiv_id":"2504.05804","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-bert-gradient-attack-on-twitter","slug":"breaking-bert-gradient-attack-on-twitter","title":"Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted Misclassification","date":"2025-04-02","arxiv_id":"2504.01345","repositories_listed":1,"syntology":null},{"url":"/paper/smab-mab-based-word-sensitivity-estimation","slug":"smab-mab-based-word-sensitivity-estimation","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","date":"2025-02-10","arxiv_id":"2502.07101","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/smab-mab-based-word-sensitivity-estimation#ran","syntology_url":"https://syntology.ai/paper/2502.07101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07101"}},"official":{"repos":["skp1999/SMAB"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/empra-embedding-perturbation-rank-attack","slug":"empra-embedding-perturbation-rank-attack","title":"EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models","date":"2024-12-20","arxiv_id":"2412.16382","repositories_listed":1,"syntology":null},{"url":"/paper/binaryselect-to-improve-accessibility-of","slug":"binaryselect-to-improve-accessibility-of","title":"BinarySelect to Improve Accessibility of Black-Box Attack Research","date":"2024-12-13","arxiv_id":"2412.10617","repositories_listed":1,"syntology":null},{"url":"/paper/tscheater-generating-high-quality-tibetan","slug":"tscheater-generating-high-quality-tibetan","title":"TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity","date":"2024-12-03","arxiv_id":"2412.02371","repositories_listed":1,"syntology":null},{"url":"/paper/nmt-obfuscator-attack-ignore-a-sentence-in","slug":"nmt-obfuscator-attack-ignore-a-sentence-in","title":"NMT-Obfuscator Attack: Ignore a sentence in translation with only one word","date":"2024-11-19","arxiv_id":"2411.12473","repositories_listed":1,"syntology":null},{"url":"/paper/advi2i-adversarial-image-attack-on-image-to","slug":"advi2i-adversarial-image-attack-on-image-to","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","date":"2024-10-28","arxiv_id":"2410.21471","repositories_listed":1,"syntology":null},{"url":"/paper/controlled-generation-of-natural-adversarial","slug":"controlled-generation-of-natural-adversarial","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","date":"2024-10-03","arxiv_id":"2410.02163","repositories_listed":1,"syntology":null},{"url":"/paper/vision-fused-attack-advancing-aggressive-and","slug":"vision-fused-attack-advancing-aggressive-and","title":"Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation","date":"2024-09-08","arxiv_id":"2409.05021","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/vision-fused-attack-advancing-aggressive-and#ran","syntology_url":"https://syntology.ai/paper/2409.05021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05021"}},"official":{"repos":["levelower/vfa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/2408-00312","slug":"2408-00312","title":"Adversarial Text Rewriting for Text-aware Recommender Systems","date":"2024-08-01","arxiv_id":"2408.00312","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attacks-on-multimodal-agents","slug":"adversarial-attacks-on-multimodal-agents","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","date":"2024-06-18","arxiv_id":"2406.12814","repositories_listed":1,"syntology":{"n":21,"n_ran":16,"n_constructed":0,"n_ran_checked":6,"n_instrument":10,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/adversarial-attacks-on-multimodal-agents#ran","syntology_url":"https://syntology.ai/paper/2406.12814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12814"}},"official":{"repos":["chenwu98/agent-attack"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/white-box-multimodal-jailbreaks-against-large","slug":"white-box-multimodal-jailbreaks-against-large","title":"White-box Multimodal Jailbreaks Against Large Vision-Language Models","date":"2024-05-28","arxiv_id":"2405.17894","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/white-box-multimodal-jailbreaks-against-large#ran","syntology_url":"https://syntology.ai/paper/2405.17894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17894"}},"official":{"repos":["roywang021/UMK"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-adversarial-robustness-of","slug":"revisiting-the-adversarial-robustness-of","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","date":"2024-04-30","arxiv_id":"2404.19287","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":6,"n_instrument":12,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/revisiting-the-adversarial-robustness-of#ran","syntology_url":"https://syntology.ai/paper/2404.19287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19287"}},"official":{"repos":["ellezwq/mmcoa"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-adversarial-prompt-learning-on","slug":"few-shot-adversarial-prompt-learning-on","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","date":"2024-03-21","arxiv_id":"2403.14774","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/few-shot-adversarial-prompt-learning-on#ran","syntology_url":"https://syntology.ai/paper/2403.14774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14774"}},"official":{"repos":["lionel-w2/fap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-transferability-in-vision-language","slug":"boosting-transferability-in-vision-language","title":"Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory","date":"2024-03-19","arxiv_id":"2403.12445","repositories_listed":1,"syntology":null},{"url":"/paper/a-curious-case-of-searching-for-the","slug":"a-curious-case-of-searching-for-the","title":"A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models","date":"2024-02-18","arxiv_id":"2402.11469","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-synonym-bert-based-adversarial","slug":"arabic-synonym-bert-based-adversarial","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","date":"2024-02-05","arxiv_id":"2402.03477","repositories_listed":1,"syntology":null},{"url":"/paper/bert-lost-patience-won-t-be-robust-to-1","slug":"bert-lost-patience-won-t-be-robust-to-1","title":"BERT Lost Patience Won't Be Robust to Adversarial Slowdown","date":"2023-10-29","arxiv_id":"2310.19152","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bert-lost-patience-won-t-be-robust-to-1#ran","syntology_url":"https://syntology.ai/paper/2310.19152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19152"}},"official":{"repos":["ztcoalson/waffle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/votetrans-detecting-adversarial-text-without","slug":"votetrans-detecting-adversarial-text-without","title":"VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations","date":"2023-06-02","arxiv_id":"2306.01273","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-removing-text-regions-improves","slug":"less-is-more-removing-text-regions-improves","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","date":"2023-05-08","arxiv_id":"2305.05095","repositories_listed":1,"syntology":null},{"url":"/paper/a-pilot-study-of-query-free-adversarial","slug":"a-pilot-study-of-query-free-adversarial","title":"A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion","date":"2023-03-29","arxiv_id":"2303.16378","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-pilot-study-of-query-free-adversarial#ran","syntology_url":"https://syntology.ai/paper/2303.16378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16378"}},"official":{"repos":["optml-group/qf-attack"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/frauds-bargain-attack-generating-adversarial","slug":"frauds-bargain-attack-generating-adversarial","title":"Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process","date":"2023-03-01","arxiv_id":"2303.01234","repositories_listed":1,"syntology":null},{"url":"/paper/retvec-resilient-and-efficient-text","slug":"retvec-resilient-and-efficient-text","title":"RETVec: Resilient and Efficient Text Vectorizer","date":"2023-02-18","arxiv_id":"2302.09207","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/retvec-resilient-and-efficient-text#ran","syntology_url":"https://syntology.ai/paper/2302.09207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09207"}},"official":{"repos":["google-research/retvec"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/step-by-step-loss-goes-very-far-multi-step","slug":"step-by-step-loss-goes-very-far-multi-step","title":"Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks","date":"2023-02-10","arxiv_id":"2302.05120","repositories_listed":1,"syntology":null},{"url":"/paper/riatig-reliable-and-imperceptible-adversarial","slug":"riatig-reliable-and-imperceptible-adversarial","title":"RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ignore-previous-prompt-attack-techniques-for","slug":"ignore-previous-prompt-attack-techniques-for","title":"Ignore Previous Prompt: Attack Techniques For Language Models","date":"2022-11-17","arxiv_id":"2211.09527","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ignore-previous-prompt-attack-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2211.09527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09527"}},"official":{"repos":["agencyenterprise/promptinject"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/tape-assessing-few-shot-russian-language","slug":"tape-assessing-few-shot-russian-language","title":"TAPE: Assessing Few-shot Russian Language Understanding","date":"2022-10-23","arxiv_id":"2210.12813","repositories_listed":1,"syntology":null},{"url":"/paper/semattack-natural-textual-attacks-via-1","slug":"semattack-natural-textual-attacks-via-1","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-05-03","arxiv_id":"2205.01287","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semattack-natural-textual-attacks-via-1#ran","syntology_url":"https://syntology.ai/paper/2205.01287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01287"}},"official":{"repos":["ai-secure/semattack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/that-is-a-suspicious-reaction-interpreting-1","slug":"that-is-a-suspicious-reaction-interpreting-1","title":"\"That Is a Suspicious Reaction!\": Interpreting Logits Variation to Detect NLP Adversarial Attacks","date":"2022-04-10","arxiv_id":"2204.04636","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-of-neural-statistical","slug":"adversarial-robustness-of-neural-statistical","title":"Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers","date":"2022-03-02","arxiv_id":"2203.07983","repositories_listed":1,"syntology":null},{"url":"/paper/sepp-similarity-estimation-of-predicted","slug":"sepp-similarity-estimation-of-predicted","title":"SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text","date":"2021-10-12","arxiv_id":"2110.05748","repositories_listed":1,"syntology":null},{"url":"/paper/mate-kd-masked-adversarial-text-a-companion","slug":"mate-kd-masked-adversarial-text-a-companion","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","date":"2021-05-12","arxiv_id":"2105.05912","repositories_listed":1,"syntology":null},{"url":"/paper/persistent-anti-muslim-bias-in-large-language","slug":"persistent-anti-muslim-bias-in-large-language","title":"Persistent Anti-Muslim Bias in Large Language Models","date":"2021-01-14","arxiv_id":"2101.05783","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-to-real-unsupervised-domain-1","slug":"synthetic-to-real-unsupervised-domain-1","title":"Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild","date":"2020-09-03","arxiv_id":"2009.01766","repositories_listed":1,"syntology":null},{"url":"/paper/190807899","slug":"190807899","title":"Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples","date":"2019-08-21","arxiv_id":"1908.07899","repositories_listed":1,"syntology":null},{"url":"/paper/textbugger-generating-adversarial-text","slug":"textbugger-generating-adversarial-text","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","date":"2018-12-13","arxiv_id":"1812.05271","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-attacks-and-submodular-optimization","slug":"discrete-attacks-and-submodular-optimization","title":"Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification","date":"2018-12-01","arxiv_id":"1812.00151","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discrete-attacks-and-submodular-optimization#ran","syntology_url":"https://syntology.ai/paper/1812.00151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00151"}},"official":{"repos":["cecilialeiqi/adversarial_text"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-text-generation-via-feature","slug":"adversarial-text-generation-via-feature","title":"Adversarial Text Generation via Feature-Mover's Distance","date":"2018-09-17","arxiv_id":"1809.06297","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-text-generation-via-feature#ran","syntology_url":"https://syntology.ai/paper/1809.06297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06297"}},"official":null}},{"url":"/paper/dancin-seq2seq-fooling-text-classifiers-with","slug":"dancin-seq2seq-fooling-text-classifiers-with","title":"DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation","date":"2017-12-14","arxiv_id":"1712.05419","repositories_listed":1,"syntology":null},{"url":null,"slug":"adversarial-text-generation-with-dynamic","title":"Adversarial Text Generation with Dynamic Contextual Perturbation","date":"2025-06-10","arxiv_id":"2506.09148","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-grey-box-text-attack-framework-using","title":"A Grey-box Text Attack Framework using Explainable AI","date":"2025-03-11","arxiv_id":"2503.08226","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-adversarial-text-representation","title":"Continuous Adversarial Text Representation Learning for Affective Recognition","date":"2025-02-28","arxiv_id":"2502.20613","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-lexical-manifold-projection-in","title":"Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation","date":"2025-02-08","arxiv_id":"2502.05395","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-a-wolf-in-sheep-s-clothing-combating","title":"Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization","date":"2024-12-15","arxiv_id":"2412.12212","repositories_listed":0,"syntology":null},{"url":null,"slug":"bamba-a-bimodal-adversarial-multi-round-black","title":"PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization","date":"2024-12-08","arxiv_id":"2412.05892","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenetap-scene-coherent-typographic","title":"SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments","date":"2024-11-28","arxiv_id":"2412.00114","repositories_listed":0,"syntology":null},{"url":null,"slug":"iae-irony-based-adversarial-examples-for","title":"IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems","date":"2024-11-12","arxiv_id":"2411.07850","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-driven-attack-for-large-language","title":"Target-driven Attack for Large Language Models","date":"2024-11-09","arxiv_id":"2411.07268","repositories_listed":0,"syntology":null},{"url":null,"slug":"suspiciousness-of-adversarial-texts-to-human","title":"Graded Suspiciousness of Adversarial Texts to Human","date":"2024-10-06","arxiv_id":"2410.04377","repositories_listed":0,"syntology":null},{"url":null,"slug":"openfact-at-checkthat-2024-combining-multiple","title":"OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation","date":"2024-09-04","arxiv_id":"2409.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-llm-enhanced-adversarial-attack","title":"Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion","date":"2024-08-01","arxiv_id":"2408.00352","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21073","title":"Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent","date":"2024-07-29","arxiv_id":"2407.21073","repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-t2i-challenge-can-text-to-image","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","date":"2024-06-11","arxiv_id":"2406.07546","repositories_listed":0,"syntology":null},{"url":null,"slug":"phantom-general-trigger-attacks-on-retrieval","title":"Phantom: General Trigger Attacks on Retrieval Augmented Language Generation","date":"2024-05-30","arxiv_id":"2405.20485","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-a-c-e-robust-adversarial-concept-erasure","title":"R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model","date":"2024-05-25","arxiv_id":"2405.16341","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-stealth-adversarial-text-attacks-on","title":"Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods","date":"2024-04-08","arxiv_id":"2404.05159","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-guided-generative-prompt-injection","title":"Goal-guided Generative Prompt Injection Attack on Large Language Models","date":"2024-04-06","arxiv_id":"2404.07234","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-purification-a-large","title":"Adversarial Text Purification: A Large Language Model Approach for Defense","date":"2024-02-05","arxiv_id":"2402.06655","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-to-continuous-image","title":"Adversarial Text to Continuous Image Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-robust-detection-of-language-model","title":"Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?","date":"2023-06-09","arxiv_id":"2306.05871","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-humans-perceive-adversarial-text-a","title":"How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks","date":"2023-05-24","arxiv_id":"2305.15587","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-adversarial-attack-on-image-guided","title":"Iterative Adversarial Attack on Image-guided Story Ending Generation","date":"2023-05-16","arxiv_id":"2305.13208","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-imperceptible-document-manipulations","title":"Towards Imperceptible Document Manipulations against Neural Ranking Models","date":"2023-05-03","arxiv_id":"2305.01860","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-training-of-mixture-of-experts","title":"Improved Training of Mixture-of-Experts Language GANs","date":"2023-02-23","arxiv_id":"2302.11875","repositories_listed":0,"syntology":null},{"url":null,"slug":"textdefense-adversarial-text-detection-based","title":"TextDefense: Adversarial Text Detection based on Word Importance Entropy","date":"2023-02-12","arxiv_id":"2302.05892","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-text-generation-using-generative","title":"A survey on text generation using generative adversarial networks","date":"2022-12-20","arxiv_id":"2212.11119","repositories_listed":0,"syntology":null},{"url":null,"slug":"parse-an-efficient-search-method-for-black","title":"PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-normalization","title":"Adversarial Text Normalization","date":"2022-06-08","arxiv_id":"2206.04137","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-word-level-adversarial-text-attacks","title":"Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"that-is-a-suspicious-reaction-interpreting-2","title":"“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-mitigation-of-adversarial-text","title":"Data-Driven Mitigation of Adversarial Text Perturbation","date":"2022-02-19","arxiv_id":"2202.09483","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-adversarial-attacks-on-text","title":"Identifying Adversarial Attacks on Text Classifiers","date":"2022-01-21","arxiv_id":"2201.08555","repositories_listed":0,"syntology":null},{"url":null,"slug":"semattack-natural-textual-attacks-via","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"repairing-adversarial-texts-through","title":"Repairing Adversarial Texts through Perturbation","date":"2021-12-29","arxiv_id":"2201.02504","repositories_listed":0,"syntology":null},{"url":null,"slug":"that-is-a-suspicious-reaction-interpreting","title":"\"That Is a Suspicious Reaction!\": Interpreting Logits Variation to Detect NLP Adversarial Attacks","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dont-search-for-a-search-method-simple","title":"Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-adversarial-text-generation-with-n","title":"Improving Adversarial Text Generation with n-Gram Matching","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-models-know-about-their-attackers","title":"What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-watermarked-adversarial-texts","title":"Generating Watermarked Adversarial Texts","date":"2021-10-25","arxiv_id":"2110.12948","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-a-simple-and-efficient","title":"Adversarial Training: A simple and efficient technique to Improving NLP Robustness","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-search-for-a-search-method-simple","title":"Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks","date":"2021-09-16","arxiv_id":"2109.07926","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforce-attack-adversarial-attack-against","title":"Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disco-efficient-unsupervised-decoding-for","title":"DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation","date":"2021-07-07","arxiv_id":"2107.05380","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-adversarial-text-attacks-via","title":"Detecting Adversarial Text Attacks via SHapley Additive exPlanations","date":"2021-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tl-dr-out-of-context-adversarial-text","title":"\"TL;DR:\" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation","date":"2021-04-01","arxiv_id":"2104.00782","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-to-image-synthesis-a-review","title":"Adversarial Text-to-Image Synthesis: A Review","date":"2021-01-25","arxiv_id":"2101.09983","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-unsupervised-machine-translation-to","title":"From Unsupervised Machine Translation To Adversarial Text Generation","date":"2020-11-10","arxiv_id":"2011.05449","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-generation-via-sequence","title":"Adversarial Text Generation via Sequence Contrast Discrimination","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/task/adversarial-text/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/adversarial-text/papers/2","json":"/task/adversarial-text/papers/2.json","rows":14},{"order":"ran","page":1,"of":1,"url":"/task/adversarial-text/papers/ran/1","json":"/task/adversarial-text/papers/ran/1.json","rows":16}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"f397c7218e477211b6419b6eeab2f9b689bee72eaaba22a357baacd1f8256045","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}