# Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense

arXiv: https://arxiv.org/abs/2402.18787 · HTML: https://mlsanity.com/paper/2402.18787/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 36)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [Towards Robust Neural Networks via Random Self-ensemble](https://mlsanity.com/paper/1712.00673/) (2017)
- [DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning](https://mlsanity.com/paper/2106.03760/) (2021)
- [The Consciousness Prior](https://mlsanity.com/paper/1709.08568/) (2017)
- [ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples](https://mlsanity.com/paper/1811.12673/) (2018)
- [When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks](https://mlsanity.com/paper/1911.10695/) (2019)
- [Deflecting Adversarial Attacks with Pixel Deflection](https://mlsanity.com/paper/1801.08926/) (2018)
- [Learning Disentangled Representations via Mutual Information Estimation](https://mlsanity.com/paper/1912.03915/) (2019)
- [SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization](https://mlsanity.com/paper/2006.14255/) (2020)
- [Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack](https://mlsanity.com/paper/2203.05154/) (2022)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)

## Built on by (most cited first, 3 of 3)

- [Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation](https://mlsanity.com/paper/2412.11608/) (2024)
- [Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts](https://mlsanity.com/paper/2602.01369/) (2026)
- [Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Training](https://mlsanity.com/paper/2512.20821/) (2025)

## Abstract (arXiv)

Recent studies have revealed the vulnerability of Deep Neural Networks (DNNs) to adversarial examples, which can easily fool DNNs into making incorrect predictions. To mitigate this deficiency, we propose a novel adversarial defense method called "Immunity" (Innovative MoE with MUtual information & positioN stabilITY) based on a modified Mixture-of-Experts (MoE) architecture in this work. The key enhancements to the standard MoE are two-fold: 1) integrating of Random Switch Gates (RSGs) to obtain diverse network structures via random permutation of RSG parameters at evaluation time, despite of RSGs being determined after one-time training; 2) devising innovative Mutual Information (MI)-based and Position Stability-based loss functions by capitalizing on Grad-CAM's explanatory power to increase the diversity and the causality of expert networks. Notably, our MI-based loss operates directly on the heatmaps, thereby inducing subtler negative impacts on the classification performance when compared to other losses of the same type, theoretically. Extensive evaluation validates the efficacy of the proposed approach in improving adversarial robustness against a wide range of attacks.