# A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models

arXiv: https://arxiv.org/abs/2407.14114 · HTML: https://mlsanity.com/paper/2407.14114/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 53 references that are in the map.
- First posted on arXiv 19 Jul 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [On Detecting Adversarial Perturbations](https://mlsanity.com/paper/1702.04267/) (2017)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [On the (Statistical) Detection of Adversarial Examples](https://mlsanity.com/paper/1702.06280/) (2017)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Deep Neural Rejection against Adversarial Examples](https://mlsanity.com/paper/1910.00470/) (2019)
- [Test Selection for Deep Learning Systems](https://mlsanity.com/paper/1904.13195/) (2019)
- [Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection](https://mlsanity.com/paper/2012.05329/) (2020)
- [Uncertainty-Aware Attention for Reliable Interpretation and Prediction](https://mlsanity.com/paper/1805.09653/) (2018)
- [Distribution-Aware Testing of Neural Networks Using Generative Models](https://mlsanity.com/paper/2102.13602/) (2021)
- [Failure Prediction for Autonomous Driving](https://mlsanity.com/paper/1805.01811/) (2018)
- [Exposing Previously Undetectable Faults in Deep Neural Networks](https://mlsanity.com/paper/2106.00576/) (2021)
- [Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion](https://mlsanity.com/paper/2112.01955/) (2021)
- [Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation](https://mlsanity.com/paper/2207.10942/) (2022)

## Built on by (most cited first, 1 of 1)

- [What Paired Evaluations Reveal under Visual Perturbations](https://mlsanity.com/paper/2609.35583/) (2026)

## Abstract (arXiv)

Sharpening deep learning models by training them with examples close to the decision boundary is a well-known best practice. Nonetheless, these models are still error-prone in producing predictions. In practice, the inference of the deep learning models in many application systems is guarded by a rejector, such as a confidence-based rejector, to filter out samples with insufficient prediction confidence. Such confidence-based rejectors cannot effectively guard against failing samples with high confidence. Existing test case prioritization techniques effectively distinguish confusing samples from confident samples to identify failing samples among the confusing ones, yet prioritizing the failing ones high among many confident ones is challenging. In this paper, we propose A3Rank, a novel test case prioritization technique with augmentation alignment analysis, to address this problem. A3Rank generates augmented versions of each test case and assesses the extent of the prediction result for the test case misaligned with these of the augmented versions and vice versa. Our experiment shows that A3Rank can effectively rank failing samples escaping from the checking of confidence-based rejectors, which significantly outperforms the peer techniques by 163.63% in the detection ratio of top-ranked samples. We also provide a framework to construct a detector devoted to augmenting these rejectors to defend these failing samples, and our detector can achieve a significantly higher defense success rate.