# PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches

Source: [PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches](<https://www.sota2.com/research/paper/68fa79031e209131cea7bab2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:25:09.405Z

Authors: Dennis Jacob, Chong Xiang, Prateek Mittal

Published: 2025-05-30T15:25:51.000Z

## Abstract

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of these attacks calls for certifiable defenses, which feature provable guarantees on robustness. While certifiable defenses have been successfully applied to single-label classification, limited work has been done for multi-label classification. In this work, we present PatchDEMUX, a certifiably robust framework for multi-label classifiers against adversarial patches. Our approach is a generalizable method which can extend any existing certifiable defense for single-label classification; this is done by considering the multi-label classification task as a series of isolated binary classification problems to provably guarantee robustness. Furthermore, in the scenario where an attacker is limited to a single patch we propose an additional certification procedure that can provide tighter robustness bounds. Using the current state-of-the-art (SOTA) single-label certifiable defense PatchCleanser as a backbone, we find that PatchDEMUX can achieve non-trivial robustness on the MS-COCO and PASCAL VOC datasets while maintaining high clean performance

## 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.

- [Object Detection on PASCAL VOC 2007 (val) with Certified Recall Metrics](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-2007-val-with-certified-recall-metrics.md>): Object Detection; PASCAL VOC 2007 (val); Precision @ 25% CR: 90.591.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.24703>)

[PDF](<https://arxiv.org/pdf/2505.24703.pdf>)

[Implementation](<https://github.com/inspire-group/PatchDEMUX>)