mlsanityData to 7 Oct 2026

Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation

arXiv 2412.11608 ↗First posted 16 Dec 2024cs.CV cs.LGcited by 5

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Vulnerability to adversarial attacks is a well-known deficiency of deep neural networks. Larger networks are generally more robust, and ensembling is one method to increase adversarial robustness: each model's weaknesses are compensated by the strengths of others. While an ensemble uses a deterministic rule to combine model outputs, a mixture of experts (MoE) includes an additional learnable gating component that predicts weights for the outputs of the expert models, thus determining their contributions to the final prediction. MoEs have been shown to outperform ensembles on specific tasks, yet their susceptibility to adversarial attacks has not been studied yet. In this work, we evaluate the adversarial vulnerability of MoEs for semantic segmentation of urban and highway traffic scenes. We show that MoEs are, in most cases, more robust to per-instance and universal white-box adversarial attacks and can better withstand transfer attacks. Our code is available at urlhttps://github.com/KASTEL-MobilityLab/mixtures-of-experts/.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 34 of its 44 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

34 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense29 Feb
  2. 2023Robust Mixture-of-Expert Training for Convolutional Neural Networks19 Aug
  3. 2022On the Adversarial Robustness of Mixture of Experts19 Oct
  4. 2022Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability22 Apr

Other references · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
18 more
  1. 2016Adversarial examples in the physical worldcited by 1,762
  2. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  3. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 400
  4. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  5. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  6. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  7. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  8. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  9. 2016Full-Resolution Residual Networks for Semantic Segmentation in Street Scenescited by 71
  10. 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69
  11. 2016Network of Experts for Large-Scale Image Categorizationcited by 54
  12. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  13. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  14. 2017Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networkscited by 31
  15. 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
  16. 2021Adversarial Examples on Segmentation Models Can be Easy to Transfercited by 15
  17. 2022Improving robustness and calibration in ensembles with diversity regularizationcited by 8
  18. 2021Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbationscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  2. 2025Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentationcited by 6
  3. 2025Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Trainingcited by 1
  4. 2026MME: Mixture of Mesh Experts with Random Walk Transformer Gatingcited by 0
  5. 2026RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
  2. 2025Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
  3. 2026Domain-Specialized Object Detection via Model-Level Mixtures of Experts
  4. 2026Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
  5. 2024Mixture of Experts in Image Classification: What's the Sweet Spot?
  6. 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
  7. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  8. 2026The Rise of Sparse Mixture-of-Experts: A Survey from Algorithmic Foundations to Decentralized Architectures and Vertical Domain Applications