# Locally optimal detection of stochastic targeted universal adversarial perturbations

Source: [Locally optimal detection of stochastic targeted universal adversarial perturbations](<https://www.sota2.com/research/paper/68fa68db1e209131cea1eba0>)

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

Data updated: 2025-10-25T22:47:52.778Z

Authors: Amish Goel, Pierre Moulin

Published: 2020-12-08T19:27:39.000Z

## Abstract

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test (LO-GLRT) based detector for detecting stochastic targeted universal adversarial perturbations (UAPs) of the classifier inputs. We also describe a supervised training method to learn the detector's parameters, and demonstrate better performance of the detector compared to other detection methods on several popular image classification datasets.

## 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](<https://arxiv.org/abs/2012.04692>)

[PDF](<https://arxiv.org/pdf/2012.04692.pdf>)