{"url":"/task/dnn-testing","name":"DNN Testing","slug":"dnn-testing","description_markdown":"Testing the reliability of DNNs.","categories":[{"name":"Adversarial","url":"/area/adversarial"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":27,"papers_with_code":10,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":10,"of":10,"tagged_in_all":27,"items":[{"url":"/paper/rbr4dnn-requirements-based-testing-of-neural","title":"RBT4DNN: Requirements-based Testing of Neural Networks","date":"2025-04-03","arxiv_id":"2504.02737","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-system-boundary-testing-through","title":"Targeted Deep Learning System Boundary Testing","date":"2024-08-12","arxiv_id":"2408.06258","repositories_listed":1,"syntology":null},{"url":"/paper/an-overview-of-structural-coverage-metrics","title":"An Overview of Structural Coverage Metrics for Testing Neural Networks","date":"2022-08-05","arxiv_id":"2208.03407","repositories_listed":1,"syntology":null},{"url":"/paper/black-box-testing-of-deep-neural-networks","title":"Black-Box Testing of Deep Neural Networks Through Test Case Diversity","date":"2021-12-20","arxiv_id":"2112.12591","repositories_listed":1,"syntology":null},{"url":"/paper/you-can-t-see-the-forest-for-its-trees","title":"Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion","date":"2021-12-03","arxiv_id":"2112.01955","repositories_listed":1,"syntology":null},{"url":"/paper/perception-matters-detecting-perception","title":"Perception Matters: Detecting Perception Failures of VQA Models Using Metamorphic Testing","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distribution-aware-testing-of-neural-networks","title":"Distribution-Aware Testing of Neural Networks Using Generative Models","date":"2021-02-26","arxiv_id":"2102.13602","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-robustness-analysis-for-dnns","title":"Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning","date":"2021-01-25","arxiv_id":"2101.10102","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-operational-dnn-testing-efficiency","title":"Boosting Operational DNN Testing Efficiency through Conditioning","date":"2019-06-06","arxiv_id":"1906.02533","repositories_listed":1,"syntology":null},{"url":"/paper/testing-deep-neural-network-based-image","title":"Testing DNN Image Classifiers for Confusion & Bias Errors","date":"2019-05-20","arxiv_id":"1905.07831","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}