mlsanityData to 7 Oct 2026

Private and Reliable Neural Network Inference

arXiv 2210.15614 ↗First posted 27 Oct 2022cs.LG cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been largely disconnected, yet their combination will be increasingly important. In this work, we present the first system which enables privacy-preserving inference on reliable NNs. Our key idea is to design efficient fully homomorphic encryption (FHE) counterparts for the core algorithmic building blocks of randomized smoothing, a state-of-the-art technique for obtaining reliable models. The lack of required control flow in FHE makes this a demanding task, as na"ive solutions lead to unacceptable runtime. We employ these building blocks to enable privacy-preserving NN inference with robustness and fairness guarantees in a system called Phoenix. Experimentally, we demonstrate that Phoenix achieves its goals without incurring prohibitive latencies. To our knowledge, this is the first work which bridges the areas of client data privacy and reliability guarantees for NNs.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 63 of its 125 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

63 of 125 references.

References · 63

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019Natural Adversarial Examplescited by 1,401
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  11. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  12. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
38 more
  1. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  2. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  3. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  4. 2019On Evaluating Adversarial Robustnesscited by 442
  5. 2017Algorithmic decision making and the cost of fairnesscited by 402
  6. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  7. 2020Fairness in Machine Learning: A Surveycited by 369
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  9. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  10. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  11. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  12. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  13. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  14. 2020Blind Backdoors in Deep Learning Modelscited by 174
  15. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  16. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  17. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  18. 2020Data-Free Model Extractioncited by 121
  19. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  20. 2020Learning Certified Individually Fair Representationscited by 69
  21. 2018Low Latency Privacy Preserving Inferencecited by 57
  22. 2021Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Networkcited by 57
  23. 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
  24. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  25. 2020Certified Defense to Image Transformations via Randomized Smoothingcited by 51
  26. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  27. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  28. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
  29. 2020Learning perturbation sets for robust machine learningcited by 48
  30. 2020Detection as Regression: Certified Object Detection by Median Smoothingcited by 47
  31. 2018Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inferencecited by 45
  32. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
  33. 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 39
  34. 2019SHE: A Fast and Accurate Deep Neural Network for Encrypted Datacited by 36
  35. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  36. 2021CaPC Learning: Confidential and Private Collaborative Learningcited by 33
  37. 2018nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Datacited by 24
  38. 2021HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecturecited by 24

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 3; 2026: 1.

6 papers.

  1. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  2. 2023TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecturecited by 4
  3. 2025Efficient Decoding Methods for Language Models on Encrypted Datacited by 2
  4. 2025SecPE: Secure Prompt Ensembling for Private and Robust Large Language Modelscited by 0
  5. 2025Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Modelscited by 0
  6. 2026Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inferencecited by 0