Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessConformal PredictionPredictionUncertainty QuantificationvalidMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide suf…
Adversarial AttackAdversarial RobustnessConformal PredictionPredictionGame Theoretic Mixed Experts for Combinational Adversarial Machine Learning
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defense…
Adversarial DefenseFedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
Federated learning (FL) provides a distributed training paradigm where multiple clients can jointly train a global model without sharing their local data. However, recent studies have shown that FL offers an additional s…
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…
Backdoor AttackGame Theory for Adversarial Attacks and Defenses
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect…
Adversarial DefenseDenoisingDiversitySuper-Resolution