Evaluating Ensemble Robustness Against Adversarial Attacks
Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of transferability poses grave security concerns as it leads to the possibility of attacking models in a black box setting, during which the internal parameters of the target model are unknown. In this paper, we seek to analyze and minimize the transferability of adversaries between models within an ensemble. To this end, we introduce a gradient based measure of how effectively an ensemble's constituent models collaborate to reduce the space of adversarial examples targeting the ensemble itself. Furthermore, we demonstrate that this measure can be utilized during training as to increase an ensemble's robustness to adversarial examples.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Er…
Adversarial RobustnessDiversityResilience to Multiple Attacks via Adversarially Trained MIMO Ensembles
While ensemble methods have been widely used for robustness against random perturbations (\ie the average case), ensemble approaches for robustness against adversarial perturbations (\ie the worst case) have remained elu…
Adversarial RobustnessFast Proxies for LLM Robustness Evaluation
Evaluating the robustness of LLMs to adversarial attacks is crucial for safe deployment, yet current red-teaming methods are often prohibitively expensive. We compare the ability of fast proxy metrics to predict the real…
Red TeamingHeterogeneous Architecture Search Approach within Adversarial Dynamic Defense Framework
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks (DNNs). To address this issue, various methods have been proposed to design network architectures that are robust …
Adversarial AttackAdversarial RobustnessDiversityJacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with …