{"url":"/dataset/tcab","name":"TCAB","full_name":"Text Classification Attack Benchmark","description_markdown":"Text Classification Attack Benchmark (TCAB) is a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve adversarial attack targeting three classifiers trained on six source datasets for sentiment analysis and abuse detection in English. The process of generating attacks is automated, so that TCAB can easily be extended to incorporate new text attacks and better classifiers as they are developed.\r\n\r\nSource: [TCAB: A Large-Scale Text Classification Attack Benchmark](https://arxiv.org/pdf/2210.12233v1.pdf)","description_withheld":null,"homepage":"https://github.com/react-nlp/tcab_generation","introduced_date":"2022-10-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/tcab-a-large-scale-text-classification-attack","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","first_author":"Kalyani Asthana","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/REACT-NLP/tcab_generation/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Adversarial Attack","url":"/task/adversarial-attack","datasets_with_task":"/datasets/task/adversarial-attack"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TCAB"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}