# Houdini: Fooling Deep Structured Prediction Models

Source: [Houdini: Fooling Deep Structured Prediction Models](<https://www.sota2.com/research/paper/68fa63861e209131ce9ff403>)

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

Data updated: 2025-10-25T20:43:17.087Z

Authors: Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet

Published: 2017-07-17T19:11:08.000Z

## Abstract

Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In all cases, the attacks based on Houdini achieve higher success rate than those based on the traditional surrogates used to train the models while using a less perceptible adversarial perturbation.

## 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/1707.05373>)

[PDF](<https://arxiv.org/pdf/1707.05373.pdf>)