mlsanityData to 14 Oct 2026

Watermarking for Out-of-distribution Detection

arXiv 2210.15198 ↗First posted 27 Oct 2022cs.LG cs.MMcited by 28

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogramming property of deep models and thus may not fully unleash their intrinsic strength: without modifying parameters of a well-trained deep model, we can reprogram this model for a new purpose via data-level manipulation (e.g., adding a specific feature perturbation to the data). This property motivates us to reprogram a classification model to excel at OOD detection (a new task), and thus we propose a general methodology named watermarking in this paper. Specifically, we learn a unified pattern that is superimposed onto features of original data, and the model's detection capability is largely boosted after watermarking. Extensive experiments verify the effectiveness of watermarking, demonstrating the significance of the reprogramming property of deep models in OOD detection.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 52 of its 77 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

52 of 77 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2016Wide Residual Networkscited by 3,070
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2013Describing Textures in the Wildcited by 2,125
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  12. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
38 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  2. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  7. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  8. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2020Backdoor Learning: A Surveycited by 426
  12. 2019Hidden Trigger Backdoor Attackscited by 371
  13. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  14. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  15. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  16. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  17. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  18. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  19. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  20. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  21. 2021WARP: Word-level Adversarial ReProgrammingcited by 221
  22. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  23. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  24. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  25. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  26. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  27. 2018Adversarial Reprogramming of Neural Networkscited by 116
  28. 2021Can multi-label classification networks know what they don't know?cited by 100
  29. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
  30. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  31. 2020Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resourcescited by 83
  32. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  33. 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
  34. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  35. 2020Feature Space Singularity for Out-of-Distribution Detectioncited by 49
  36. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  37. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  38. 2020A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learningcited by 34

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 14; 2025: 1; 2026: 3.

28 papers.

Sort:

By area:

  1. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  2. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  3. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 32
  4. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  5. 2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
  6. 2024Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domainscited by 22
  7. 2023FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learningcited by 20
  8. 2024Sample-specific Masks for Visual Reprogramming-based Promptingcited by 18
  9. 2023Plugin estimators for selective classification with out-of-distribution detectioncited by 14
  10. 2023Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalizationcited by 12
  11. 2024Bayesian-guided Label Mapping for Visual Reprogrammingcited by 12
  12. 2023Meta OOD Learning for Continuously Adaptive OOD Detectioncited by 10
16 more
  1. 2023Moderately Distributional Exploration for Domain Generalizationcited by 8
  2. 2024RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guaranteescited by 8
  3. 2024CLIP-driven Outliers Synthesis for few-shot OOD detectioncited by 6
  4. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  5. 2024What If the Input is Expanded in OOD Detection?cited by 4
  6. 2024HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detectioncited by 3
  7. 2024Enhancing Joint Motion Prediction for Individuals with Limb Loss Through Model Reprogrammingcited by 2
  8. 2024Improving Out-of-Distribution Detection by Combining Existing Post-hoc Methodscited by 2
  9. 2025Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statisticscited by 2
  10. 2023SODA: Robust Training of Test-Time Data Adaptorscited by 1
  11. 2024BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networkscited by 1
  12. 2023Distilling the Unknown to Unveil Certaintycited by 0
  13. 2024DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protectioncited by 0
  14. 2026Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Modelcited by 0
  15. 2026Disentangled Graph Prompting for Out-Of-Distribution Detectioncited by 0
  16. 2026Neural Distribution Prior for LiDAR Out-of-Distribution Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploiting Diffusion Prior for Out-of-Distribution Detection
  2. 2025Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
  3. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
  4. 2025COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
  5. 2023Safe and Robust Watermark Injection with a Single OoD Image
  6. 2024Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
  7. 2024Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting
  8. 2024Can OOD Object Detectors Learn from Foundation Models?