{"url":"/dataset/trojvqa","name":"TrojVQA","full_name":null,"description_markdown":"A collection of 840 pretrained VQA models which may be regular “clean” models or malicious “backdoored” models which have been  trained to include a secret backdoor trigger and behavior. This collection includes models with traditional single-key backdoors as well as Dual-Key Multimodal Backdoors.\n\nFor more information, see our work “Dual-Key Multimodal Backdoors for Visual Question Answering\" (https://arxiv.org/abs/2112.07668).\n\nThis dataset is inspired by and modeled after those created by TrojAI (https://arxiv.org/abs/2003.07233). It is intended to enable the development of defensive algorithms to detect and/or purify backdoored VQA models.","description_withheld":null,"homepage":"https://github.com/SRI-CSL/TrinityMultimodalTrojAI","introduced_date":"2021-12-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/dual-key-multimodal-backdoors-for-visual","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","first_author":"Matthew Walmer","url":null},"license":{"name":"CC-BY-SA","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[],"tasks":[],"languages":[],"variants":["TrojVQA"],"data_loaders":[],"num_papers_in_archive":5,"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."}