{"url":"/task/adversarial-attack-detection","name":"Adversarial Attack Detection","slug":"adversarial-attack-detection","description_markdown":"The detection of adversarial attacks.","categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":38,"papers_with_code":16,"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":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/adversarial-attack","name":"Adversarial Attack"}],"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":16,"of":16,"tagged_in_all":38,"items":[{"url":"/paper/is-robustbench-autoattack-a-suitable","title":"Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?","date":"2021-12-02","arxiv_id":"2112.01601","repositories_listed":2,"syntology":null},{"url":"/paper/maximum-mean-discrepancy-is-aware-of","title":"Maximum Mean Discrepancy Test is Aware of Adversarial Attacks","date":"2020-10-22","arxiv_id":"2010.11415","repositories_listed":2,"syntology":null},{"url":"/paper/a-few-large-shifts-layer-inconsistency-based","title":"A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection","date":"2025-05-19","arxiv_id":"2505.12586","repositories_listed":1,"syntology":null},{"url":"/paper/neural-fingerprints-for-adversarial-attack","title":"Neural Fingerprints for Adversarial Attack Detection","date":"2024-11-07","arxiv_id":"2411.04533","repositories_listed":1,"syntology":null},{"url":"/paper/outfox-llm-generated-essay-detection-through","title":"OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples","date":"2023-07-21","arxiv_id":"2307.11729","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/graph-based-methods-coupled-with-specific","title":"Graph-based methods coupled with specific distributional distances for adversarial attack detection","date":"2023-05-31","arxiv_id":"2306.00042","repositories_listed":1,"syntology":null},{"url":"/paper/unfolding-local-growth-rate-estimates-for","title":"Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection","date":"2022-12-13","arxiv_id":"2212.06776","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-adversarial-examples-in-batches-a","title":"Detecting Adversarial Examples in Batches -- a geometrical approach","date":"2022-06-17","arxiv_id":"2206.08738","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-estimation-of-transformer","title":"Uncertainty Estimation of Transformer Predictions for Misclassification Detection","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/residue-based-natural-language-adversarial-1","title":"Residue-Based Natural Language Adversarial Attack Detection","date":"2022-04-17","arxiv_id":"2204.10192","repositories_listed":1,"syntology":null},{"url":"/paper/segment-and-complete-defending-object","title":"Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection","date":"2021-12-08","arxiv_id":"2112.04532","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/two-souls-in-an-adversarial-image-towards","title":"Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency","date":"2021-09-25","arxiv_id":"2109.12459","repositories_listed":1,"syntology":null},{"url":"/paper/towards-feature-space-adversarial-attack-1","title":"Towards Feature Space Adversarial Attack","date":"2020-04-26","arxiv_id":"2004.12385","repositories_listed":1,"syntology":null},{"url":"/paper/metaadvdet-towards-robust-detection-of","title":"MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks","date":"2019-08-06","arxiv_id":"1908.02199","repositories_listed":1,"syntology":null},{"url":"/paper/reverse-kl-divergence-training-of-prior","title":"Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness","date":"2019-05-31","arxiv_id":"1905.13472","repositories_listed":1,"syntology":null},{"url":"/paper/gotta-catch-em-all-using-concealed-trapdoors","title":"Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks","date":"2019-04-18","arxiv_id":"1904.08554","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"}}