# DDoD: Dual Denial of Decision Attacks on Human-AI Teams

arXiv: https://arxiv.org/abs/2212.03980 · HTML: https://mlsanity.com/paper/2212.03980/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 8 of 8)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI](https://mlsanity.com/paper/2010.07487/) (2020)
- [Sponge Examples: Energy-Latency Attacks on Neural Networks](https://mlsanity.com/paper/2006.03463/) (2020)
- [Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI](https://mlsanity.com/paper/1909.02309/) (2019)
- [Bad Characters: Imperceptible NLP Attacks](https://mlsanity.com/paper/2106.09898/) (2021)
- [Human Cognition through the Lens of Social Engineering Cyberattacks](https://mlsanity.com/paper/2007.04932/) (2020)

## Built on by (most cited first, 1 of 1)

- [Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach](https://mlsanity.com/paper/2412.10453/) (2024)

## Abstract (arXiv)

Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at constant risk of being attacked. While the majority of attacks targeting AI-based applications aim to manipulate classifiers or training data and alter the output of an AI model, recently proposed Sponge Attacks against AI models aim to impede the classifier's execution by consuming substantial resources. In this work, we propose textitDual Denial of Decision (DDoD) attacks against collaborative Human-AI teams. We discuss how such attacks aim to deplete textitboth computational and human resources, and significantly impair decision-making capabilities. We describe DDoD on human and computational resources and present potential risk scenarios in a series of exemplary domains.