# Identifying Model Weakness with Adversarial Examiner

arXiv: https://arxiv.org/abs/1911.11230 · HTML: https://mlsanity.com/paper/1911.11230/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation](https://mlsanity.com/paper/2302.07865/) (2023)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.10123/) (2023)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Simulated Adversarial Testing of Face Recognition Models](https://mlsanity.com/paper/2106.04569/) (2021)
- [PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.07337/) (2023)
- [Human Body Measurement Estimation with Adversarial Augmentation](https://mlsanity.com/paper/2210.05667/) (2022)
- [A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection](https://mlsanity.com/paper/2412.13913/) (2024)
- [LychSim: A Controllable and Interactive Simulation Framework for Vision Research](https://mlsanity.com/paper/2605.12449/) (2026)
- [CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts](https://mlsanity.com/paper/2507.17651/) (2025)
- [High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models](https://mlsanity.com/paper/2512.21815/) (2025)

## Abstract (arXiv)

Machine learning models are usually evaluated according to the average case performance on the test set. However, this is not always ideal, because in some sensitive domains (e.g. autonomous driving), it is the worst case performance that matters more. In this paper, we are interested in systematic exploration of the input data space to identify the weakness of the model to be evaluated. We propose to use an adversarial examiner in the testing stage. Different from the existing strategy to always give the same (distribution of) test data, the adversarial examiner will dynamically select the next test data to hand out based on the testing history so far, with the goal being to undermine the model's performance. This sequence of test data not only helps us understand the current model, but also serves as constructive feedback to help improve the model in the next iteration. We conduct experiments on ShapeNet object classification. We show that our adversarial examiner can successfully put more emphasis on the weakness of the model, preventing performance estimates from being overly optimistic.