mlsanityData to 14 Oct 2026

SMiLE: Provably Enforcing Global Relational Properties in Neural Networks

arXiv 2511.07208 ↗First posted 10 Nov 2025cs.LG cs.AI math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence systems are increasingly deployed in settings where ensuring robustness, fairness, or domain-specific properties is essential for regulation compliance and alignment with human values. However, especially on Neural Networks, property enforcement is very challenging, and existing methods are limited to specific constraints or local properties (defined around datapoints), or fail to provide full guarantees. We tackle these limitations by extending SMiLE, a recently proposed enforcement framework for NNs, to support global relational properties (defined over the entire input space). The proposed approach scales well with model complexity, accommodates general properties and backbones, and provides full satisfaction guarantees. We evaluate SMiLE on monotonicity, global robustness, and individual fairness, on synthetic and real data, for regression and classification tasks. Our approach is competitive with property-specific baselines in terms of accuracy and runtime, and strictly superior in terms of generality and level of guarantees. Overall, our results emphasize the potential of the SMiLE framework as a platform for future research and applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 61 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

25 of 61 references.

References · 25

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  4. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  5. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  6. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  7. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  8. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  9. 2017On Detecting Adversarial Perturbationscited by 232
  10. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  11. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  12. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
13 more
  1. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  2. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
  3. 2021Globally-Robust Neural Networkscited by 108
  4. 2020Understanding Catastrophic Overfitting in Single-step Adversarial Trainingcited by 76
  5. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  6. 2020Certified Monotonic Neural Networkscited by 51
  7. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 42
  8. 2022Towards Safe Reinforcement Learning with a Safety Editor Policycited by 30
  9. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  10. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  11. 2022FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networkscited by 4
  12. 2023DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfactioncited by 4
  13. 2024SMLE: Safe Machine Learning via Embedded Overapproximationcited by 1

Built on by

Not cited yet.