# Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness

arXiv: https://arxiv.org/abs/1908.11091 · HTML: https://mlsanity.com/paper/1908.11091/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [No One Representation to Rule Them All: Overlapping Features of Training Methods](https://mlsanity.com/paper/2110.12899/) (2021)
- [Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation](https://mlsanity.com/paper/2203.03057/) (2022)
- [Temperature as Uncertainty in Contrastive Learning](https://mlsanity.com/paper/2110.04403/) (2021)
- [Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance](https://mlsanity.com/paper/2402.01096/) (2024)
- [Scaling Laws for Black box Adversarial Attacks](https://mlsanity.com/paper/2411.16782/) (2024)
- [Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness](https://mlsanity.com/paper/2310.02237/) (2023)
- [Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?](https://mlsanity.com/paper/2112.04758/) (2021)
- [Hierarchical Pruning of Deep Ensembles with Focal Diversity](https://mlsanity.com/paper/2311.10293/) (2023)
- [Probing Contextual Diversity for Dense Out-of-Distribution Detection](https://mlsanity.com/paper/2208.14195/) (2022)
- [Physics-Driven ML-Based Modelling for Correcting Inverse Estimation](https://mlsanity.com/paper/2309.13985/) (2023)
- [Accurate and Efficient Two-Stage Gun Detection in Video](https://mlsanity.com/paper/2503.06317/) (2025)
- [NAPER: Fault Protection for Real-Time Resource-Constrained Deep Neural Networks](https://mlsanity.com/paper/2504.06591/) (2025)
- [Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances](https://mlsanity.com/paper/2111.07035/) (2021)
- [Evaluation of Self-taught Learning-based Representations for Facial Emotion Recognition](https://mlsanity.com/paper/2204.12624/) (2022)
- [Ensemble Learning for Healthcare: A Comparative Analysis of Hybrid Voting and Ensemble Stacking in Obesity Risk Prediction](https://mlsanity.com/paper/2509.02826/) (2025)
- [DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment](https://mlsanity.com/paper/2511.13749/) (2025)
- [A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection](https://mlsanity.com/paper/2511.16982/) (2025)
- [Virtual neural networks: hundreds of souls in a body](https://mlsanity.com/paper/2609.24782/) (2026)

## Abstract (arXiv)

Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attractive property of diversity optimized ensemble learning is its robustness against deception: an adversarial perturbation attack can mislead one DNN model to misclassify but may not fool other ensemble DNN members consistently. In this paper we first give an overview of the concept of ensemble diversity and examine the three types of ensemble diversity in the context of DNN classifiers. We then describe a set of ensemble diversity measures, a suite of algorithms for creating diversity ensembles and for performing ensemble consensus (voted or learned) for generating high accuracy ensemble output by strategically combining outputs of individual members. This paper concludes with a discussion on a set of open issues in quantifying ensemble diversity for robust deep learning.