mlsanityData to 7 Oct 2026

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing

arXiv 2411.00899 ↗First posted 1 Nov 2024cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns. Existing certified defenses for DEQs employing deterministic certification methods such as interval bound propagation and Lipschitz-bounds can not certify on large-scale datasets. Besides, they are also restricted to specific forms of DEQs. In this paper, we provide the first randomized smoothing certified defense for DEQs to solve these limitations. Our study reveals that simply applying randomized smoothing to certify DEQs provides certified robustness generalized to large-scale datasets but incurs extremely expensive computation costs. To reduce computational redundancy, we propose a novel Serialized Randomized Smoothing (SRS) approach that leverages historical information. Additionally, we derive a new certified radius estimation for SRS to theoretically ensure the correctness of our algorithm. Extensive experiments and ablation studies on image recognition demonstrate that our algorithm can significantly accelerate the certification of DEQs by up to 7x almost without sacrificing the certified accuracy. Our code is available at https://github.com/WeizhiGao/Serialized-Randomized-Smoothing.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 1 Nov 2024.

Builds on

34 of 42 references.

References · 34

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  6. 2016Adversarial Machine Learning at Scalecited by 934
  7. 2019Deep Equilibrium Modelscited by 603
  8. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  9. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  10. 2019Differentiable Convex Optimization Layerscited by 458
  11. 2019Augmented Neural ODEscited by 396
  12. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
22 more
  1. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  2. 2018Certified Defenses against Adversarial Examplescited by 305
  3. 2020Multiscale Deep Equilibrium Modelscited by 149
  4. 2019Implicit Deep Learningcited by 124
  5. 2020Monotone operator equilibrium networkscited by 100
  6. 2020Implicit Graph Neural Networkscited by 98
  7. 2021Stabilizing Equilibrium Models by Jacobian Regularizationcited by 71
  8. 2021Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Boundscited by 64
  9. 2022Deep Equilibrium Optical Flow Estimationcited by 63
  10. 2023A Unified Algebraic Perspective on Lipschitz Neural Networkscited by 58
  11. 2020Lipschitz Bounded Equilibrium Networkscited by 49
  12. 2022Deep Equilibrium Approaches to Diffusion Modelscited by 42
  13. 2021Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neuronscited by 40
  14. 2022Optimization-Induced Graph Implicit Nonlinear Diffusioncited by 28
  15. 2023TorchDEQ: A Library for Deep Equilibrium Modelscited by 21
  16. 2023Deep Equilibrium Based Neural Operators for Steady-State PDEscited by 19
  17. 2021Joint inference and input optimization in equilibrium networkscited by 15
  18. 2024Fixed Point Diffusion Modelscited by 14
  19. 2023A Closer Look at the Adversarial Robustness of Deep Equilibrium Modelscited by 13
  20. 2022Global Convergence of Over-parameterized Deep Equilibrium Modelscited by 10
  21. 2021Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approachcited by 8
  22. 2023Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamicscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Modelscited by 2
  2. 2026Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approachcited by 1