{"url":"/method/dropattack","slug":"dropattack","name":"DropAttack","full_name":"DropAttack","full_name_withheld":false,"description_markdown":"**DropAttack** is an adversarial training method that adds intentionally worst-case adversarial perturbations to both the input and hidden layers in different dimensions and minimizes the adversarial risks generated by each layer.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks","paper":"/paper/dropattack-a-masked-weight-adversarial","first_author":"Shiwen Ni","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/dropattack-a-masked-weight-adversarial"},"source":{"url":"https://arxiv.org/abs/2108.12805v1","title":"DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Adversarial Training","url":"/methods/category/adversarial-training","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/dropattack-a-masked-weight-adversarial","title":"DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks","date":"2021-08-29","arxiv_id":"2108.12805","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/adversarial-defense","name":"Adversarial Defense","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dropattack"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}