# Cross-Layer Strategic Ensemble Defense Against Adversarial Examples

arXiv: https://arxiv.org/abs/1910.01742 · HTML: https://mlsanity.com/paper/1910.01742/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance](https://mlsanity.com/paper/2402.01096/) (2024)
- [Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness](https://mlsanity.com/paper/2310.02237/) (2023)
- [Hierarchical Pruning of Deep Ensembles with Focal Diversity](https://mlsanity.com/paper/2311.10293/) (2023)
- [Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework](https://mlsanity.com/paper/2202.02626/) (2022)
- [Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems](https://mlsanity.com/paper/2307.06496/) (2023)
- [Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability](https://mlsanity.com/paper/2210.08210/) (2022)
- [A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection](https://mlsanity.com/paper/2511.16982/) (2025)

## Abstract (arXiv)

Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defense methods.