paper-with-me

홈 › Papers

Evaluating Ensemble Robustness Against Adversarial Attacks

2020-05-12 · George Adam, Romain Speciel

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.

📄 PDF Abstract BibTeX arXiv:2005.05750

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes

2023-03-04 · Thomas Philippon, Christian Gagné

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 RobustnessDiversity

Resilience to Multiple Attacks via Adversarially Trained MIMO Ensembles

2021-09-29 · Ruqi Bai, David I. Inouye, Saurabh Bagchi

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 Robustness

Fast Proxies for LLM Robustness Evaluation

2025-02-14 · Tim Beyer, Jan Schuchardt, Leo Schwinn, Stephan Günnemann

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 Teaming

Heterogeneous Architecture Search Approach within Adversarial Dynamic Defense Framework

2021-11-22 · AAAI Workshop AdvML 2022 2 · Qi Peng, Ruoxi Qin, Wenlin Liu, Libin Hou 외

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 RobustnessDiversity

Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks

2022-04-19 · Kenneth T. Co, David Martinez-Rego, Zhongyuan Hau, Emil C. Lupu

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 …