# Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation Source: [Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:57.562Z Authors: Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen Published: 2022-09-13T13:24:22.000Z ## Abstract Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentation models against this threat model. Previous work on certifiably defending against patch attacks has mostly focused on image classification task and often required changes in the model architecture and additional training which is undesirable and computationally expensive. In Demasked Smoothing, any segmentation model can be applied without particular training, fine-tuning, or restriction of the architecture. Using different masking strategies, Demasked Smoothing can be applied both for certified detection and certified recovery. In extensive experiments we show that Demasked Smoothing can on average certify 64% of the pixel predictions for a 1% patch in the detection task and 48% against a 0.5% patch for the recovery task on the ADE20K dataset. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()