mlsanityData to 14 Oct 2026

Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation

arXiv 2606.22351 ↗First posted 21 Jun 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA. SAFER preserves the wrapped TTA objective while replacing brittle single-view predictions with a reliability-guided pooled predictor. For each test sample, SAFER generates stochastic augmentations and aggregates their predictions through correlation-weighted pooling with outlier detection. We further study an adaptive-mixing extension that improves clean-performance retention by adjusting original-versus-augmentation weighting using feature disagreement signals. We evaluate on PACS, VLCS, and OfficeHome under PGD attacks at various attack rates. Across benchmarks, SAFER improves resilience of TTA methods to adversarial attacks while maintaining competitive clean performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 21 Jun 2026.

Builds on

24 of 32 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  7. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  8. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  9. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  10. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  11. 2017Countering Adversarial Images using Input Transformationscited by 520
  12. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
12 more
  1. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  3. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  4. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  5. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
  6. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  7. 2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streamscited by 63
  8. 2024Beyond Model Adaptation at Test Time: A Surveycited by 59
  9. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  10. 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentationcited by 28
  11. 2021Enhancing Adversarial Robustness via Test-time Transformation Ensemblingcited by 27
  12. 2024MedBN: Robust Test-Time Adaptation against Malicious Test Samplescited by 10

Built on by

Not cited yet.