mlsanityData to 7 Oct 2026

Smoothed Embeddings for Certified Few-Shot Learning

arXiv 2202.01186 ↗First posted 2 Feb 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not focus on the ones that learn a metric space in which classification is performed by computing distances to embeddings of classes prototypes. In this work, we extend randomized smoothing to few-shot learning models that map inputs to normalized embeddings. We provide analysis of Lipschitz continuity of such models and derive robustness certificate against ℓ2-bounded perturbations that may be useful in few-shot learning scenarios. Our theoretical results are confirmed by experiments on different datasets.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 46 of its 72 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

46 of 72 references.

References · 46

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2016Universal adversarial perturbationscited by 774
  12. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
34 more
  1. 2017One pixel attack for fooling deep neural networkscited by 579
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  3. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  4. 2018Meta-learning with differentiable closed-form solverscited by 395
  5. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  6. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  7. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  8. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  9. 2018Certified Defenses against Adversarial Examplescited by 305
  10. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  11. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  12. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  13. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  14. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  15. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  16. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  17. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  18. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  19. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  20. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  21. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  22. 2019Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifierscited by 65
  23. 2019Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablationcited by 59
  24. 2019Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothingcited by 54
  25. 2020TSS: Transformation-Specific Smoothing for Robustness Certificationcited by 49
  26. 2020Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Frameworkcited by 45
  27. 2020Higher-Order Certification for Randomized Smoothingcited by 36
  28. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  29. 2017Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Studycited by 25
  30. 2019Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attackscited by 25
  31. 2021Center Smoothing: Certified Robustness for Networks with Structured Outputscited by 18
  32. 2021CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networkscited by 18
  33. 2019Real-world adversarial attack on MTCNN face detection systemcited by 14
  34. 2021Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Taskscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2023The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothingcited by 6
  2. 2024Certification of Speaker Recognition Models to Additive Perturbationscited by 6
  3. 2024RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothingcited by 4
  4. 2025Provably Robust Adaptation for Language-Empowered Foundation Modelscited by 0
  5. 2026Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?cited by 0