paper-with-me

홈 › Papers

On the Robustness of Randomized Ensembles to Adversarial Perturbations

2023-02-02 · Hassan Dbouk, Naresh R. Shanbhag

Randomized ensemble classifiers (RECs), where one classifier is randomly selected during inference, have emerged as an attractive alternative to traditional ensembling methods for realizing adversarially robust classifiers with limited compute requirements. However, recent works have shown that existing methods for constructing RECs are more vulnerable than initially claimed, casting major doubts on their efficacy and prompting fundamental questions such as: "When are RECs useful?", "What are their limits?", and "How do we train them?". In this work, we first demystify RECs as we derive fundamental results regarding their theoretical limits, necessary and sufficient conditions for them to be useful, and more. Leveraging this new understanding, we propose a new boosting algorithm (BARRE) for training robust RECs, and empirically demonstrate its effectiveness at defending against strong $\ell_\infty$ norm-bounded adversaries across various network architectures and datasets. Our code can be found at https://github.com/hsndbk4/BARRE.

📄 PDF Abstract BibTeX arXiv:2302.01375

Code (1)

hsndbk4/barre 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Adversarial Vulnerability of Randomized Ensembles

2022-06-14 · Hassan Dbouk, Naresh R. Shanbhag

Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the real world. Recently, works on randomized e…

Adversarial AttackAdversarial RobustnessARC

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

2024-07-16 · Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu 외

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized…

Adversarial Robustness

Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

2019-12-20 · ICLR 2020 1 · Jinyuan Jia, Xiaoyu Cao, Binghui Wang, Neil Zhenqiang Gong

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses…

Promoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches

2023-10-11 · Linbo Liu, Trong Nghia Hoang, Lam M. Nguyen, Tsui-Wei Weng

Randomized smoothing has recently attracted attentions in the field of adversarial robustness to provide provable robustness guarantees on smoothed neural network classifiers. However, existing works show that vanilla ra…

Adversarial Robustness

On the Role of Randomization in Adversarially Robust Classification

2023-02-14 · NeurIPS 2023 11

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones…

Robust classification