# Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging

arXiv: https://arxiv.org/abs/2411.04376 · HTML: https://mlsanity.com/paper/2411.04376/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 62 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Uncertainty Sets for Image Classifiers using Conformal Prediction](https://mlsanity.com/paper/2009.14193/) (2020)
- [Certified Defenses for Data Poisoning Attacks](https://mlsanity.com/paper/1706.03691/) (2017)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [Least Ambiguous Set-Valued Classifiers with Bounded Error Levels](https://mlsanity.com/paper/1609.00451/) (2016)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Adversarial Risk and the Dangers of Evaluating Against Weak Attacks](https://mlsanity.com/paper/1802.05666/) (2018)
- [Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise](https://mlsanity.com/paper/1802.05300/) (2018)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [Sever: A Robust Meta-Algorithm for Stochastic Optimization](https://mlsanity.com/paper/1803.02815/) (2018)
- [RAB: Provable Robustness Against Backdoor Attacks](https://mlsanity.com/paper/2003.08904/) (2020)
- [Deep Partition Aggregation: Provable Defense against General Poisoning Attacks](https://mlsanity.com/paper/2006.14768/) (2020)
- [Learning Optimal Conformal Classifiers](https://mlsanity.com/paper/2110.09192/) (2021)
- [Robust Validation: Confident Predictions Even When Distributions Shift](https://mlsanity.com/paper/2008.04267/) (2020)
- [Data Poisoning against Differentially-Private Learners: Attacks and Defenses](https://mlsanity.com/paper/1903.09860/) (2019)
- [Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training](https://mlsanity.com/paper/2102.04716/) (2021)
- [Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection](https://mlsanity.com/paper/1802.03041/) (2018)
- [Provably Robust Conformal Prediction with Improved Efficiency](https://mlsanity.com/paper/2404.19651/) (2024)

## Built on by (most cited first, 10 of 10)

- [Dequantified Diffusion-Schr"odinger Bridge for Density Ratio Estimation](https://mlsanity.com/paper/2505.05034/) (2025)
- [AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization](https://mlsanity.com/paper/2504.01735/) (2025)
- [Conditional Conformal Risk Adaptation](https://mlsanity.com/paper/2504.07611/) (2025)
- [Volume-Sorted Prediction Set: Efficient Conformal Prediction for Multi-Target Regression](https://mlsanity.com/paper/2503.02205/) (2025)
- [Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability](https://mlsanity.com/paper/2506.07804/) (2025)
- [Enhanced Route Planning with Calibrated Uncertainty Set](https://mlsanity.com/paper/2503.10088/) (2025)
- [Fast Conformal Prediction using Conditional Interquantile Intervals](https://mlsanity.com/paper/2601.02769/) (2026)
- [Residual Reweighted Conformal Prediction for Graph Neural Networks](https://mlsanity.com/paper/2506.07854/) (2025)
- [Conformalized Large Language Models under Configuration Shift](https://mlsanity.com/paper/2608.01460/) (2026)
- [Conformal Prediction for Offensive Security](https://mlsanity.com/paper/2609.05165/) (2026)

## Abstract (arXiv)

Adversarial attacks pose significant threats to the reliability and safety of deep learning models, especially in critical domains such as medical imaging. This paper introduces a novel framework that integrates conformal prediction with game-theoretic defensive strategies to enhance model robustness against both known and unknown adversarial perturbations. We address three primary research questions: constructing valid and efficient conformal prediction sets under known attacks (RQ1), ensuring coverage under unknown attacks through conservative thresholding (RQ2), and determining optimal defensive strategies within a zero-sum game framework (RQ3). Our methodology involves training specialized defensive models against specific attack types and employing maximum and minimum classifiers to aggregate defenses effectively. Extensive experiments conducted on the MedMNIST datasets, including PathMNIST, OrganAMNIST, and TissueMNIST, demonstrate that our approach maintains high coverage guarantees while minimizing prediction set sizes. The game-theoretic analysis reveals that the optimal defensive strategy often converges to a singular robust model, outperforming uniform and simple strategies across all evaluated datasets. This work advances the state-of-the-art in uncertainty quantification and adversarial robustness, providing a reliable mechanism for deploying deep learning models in adversarial environments.